SEGMENTATION

Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages (N18-1)

Challenge:	Maintenance logbooks often contain free text fields with domain specific terms, abbreviations, and non-standard spelling . most standard NLP pipelines for pre-processing and annotation are trained on standard contemporary corpora.
Approach:	They propose to create an open-source library and data repository for predictive maintenance language datasets and to evaluate the tools available at MaintNet.
Outcome:	The proposed tools improve the performance of existing pipelines and improve the quality of the existing ones.

Copied to clipboard

Katharina Kann, Jesus Manuel Mager Hois, Ivan Vladimir Meza-Ruiz, Hinrich Schütze

Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates (P18-1)

Challenge:	Morphological segmentation for polysynthetic languages is challenging because of limited training data.
Approach:	They propose two new multi-task training approaches that improve performance for Mexican polysynthetic languages . they also propose cross-lingual transfer as a third way to fortify their neural model .
Outcome:	The proposed models improve on Mexicanero, Nahuatl, Wixarika and Yorem Nokki . the proposed models reduce the amount of parameters by close to 75% .

Copied to clipboard

Taku Kudo

Toward Unifying Text Segmentation and Long Document Summarization (2022.emnlp-main)

Challenge:	Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation.
Approach:	They propose a method to regularize subword segmentations probabilistically by sampling subwords . they also propose 'unigram' language model to be used for better subword sampling .
Outcome:	The proposed method improves on low resource and out-of-domain settings with multiple corpora.

Copied to clipboard

Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Fei Liu, Dong Yu

Information Extraction & Text Mining

Challenge:	Abstractive strategies produce more condensed summaries, but they suffer from hallucinations and factual errors, which pose a more difficult generation challenge.
Approach:	They propose a method that learns robust sentence representations by performing summarization and segmentation simultaneously, which is further enhanced by an optimization-based regularizer to promote selection of diverse summary sentences.
Outcome:	The proposed model achieves state-of-the-art performance on publicly available benchmarks and better cross-genre transferability when equipped with text segmentation.

SEDTWik: Segmentation-based Event Detection from Tweets Using Wikipedia (N19-3)

Copied to clipboard

Keval Morabia, Neti Lalita Bhanu Murthy, Aruna Malapati, Surender Samant

Information Extraction & Text Mining

Challenge:	Recent work on event detection from tweets has focused on localized events or breaking news only.
Approach:	They propose to split tweets into segments, extract bursty segments, cluster them, summarize them.
Outcome:	The proposed system can detect newsworthy events occurring at different locations of the world from a wide range of categories.

SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing (D18-2)

Copied to clipboard

Taku Kudo, John Richardson

fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP (2021.acl-demo)

Challenge:	Existing subword segmentation tools assume input is pre-tokenized into word sequences, but SentencePiece can train subword models directly from raw sentences.
Approach:	They propose a language-independent subword tokenizer and detokenizer for Neural-based text processing.
Outcome:	The proposed system achieves comparable accuracy to training from raw sentences.

Copied to clipboard

Zhichao Geng, Hang Yan, Xipeng Qiu, Xuanjing Huang

Language Models

Challenge:	Recently, the need for Chinese natural language processing (NLP) has a dramatic increase for many downstream applications.
Approach:	They propose to use Chinese word segmentation (CWS), Part-of-Speech (POS) tagging, named entity recognition (NER), and dependency parsing to train a multi-task model based on a pruned BERT.
Outcome:	The proposed model performs better than popular segmentation tools on a non-training corpus.

Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise? (2023.starsem-1)

Copied to clipboard

Xinzhe Li, Ming Liu, Shang Gao

Addressing Segmentation Ambiguity in Neural Linguistic Steganography (2022.aacl-short)

Challenge:	Existing studies have shown that Pretrained Language Models (PLMs) perform poorly under noise due to subword segmentation.
Approach:	They propose a framework for subword segmentation that provides a systematic categorization of segmentation corruption under noise and evaluation protocols by generating contrastive datasets with canonical-noisy word pairs.
Outcome:	The proposed framework provides a systematic categorization of segmentation corruption under noise and evaluation protocols by generating contrastive datasets with canonical-noisy word pairs.

Copied to clipboard

Jumon Nozaki, Yugo Murawaki

Barriers to Effective Evaluation of Simultaneous Interpretation (2024.findings-eacl)

Challenge:	Recent studies on neural linguistic steganography ignore the fact that the sender must detokenize cover texts to avoid arousing the eavesdropper’s suspicion.
Approach:	They propose to decode a secret message in a way that does not arouse suspicion of the eavesdropper.
Outcome:	The proposed techniques are applicable to languages without explicit word boundaries.

Copied to clipboard

Shira Wein, Te I, Colin Cherry, Juraj Juraska, Dirk Padfield, Wolfgang Macherey

Joint Dialogue Topic Segmentation and Categorization: A Case Study on Clinical Spoken Conversations (2023.emnlp-industry)

Challenge:	Existing studies have relied on out-of-the-box machine translation metrics to evaluate interpretation data, but they do not account for human judgments of interpretation quality.
Approach:	They propose to use machine translation metrics to evaluate human interpretations to address potential barriers to disfluency, summarization, paraphrasing and segmentation.
Outcome:	The proposed model achieves better correlation with human judgments than state-of-the-art metrics.

Copied to clipboard

Zhengyuan Liu, Siti Umairah Md Salleh, Hong Choon Oh, Pavitra Krishnaswamy, Nancy Chen

Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models (2023.findings-emnlp)

Challenge:	Utilizing natural language processing in clinical conversations is effective to improve the efficiency of workflows for medical staff and patients.
Approach:	They propose a model for dialogue segmentation and topic categorization that integrates natural language processing techniques into a joint model.
Outcome:	The proposed model improves on follow-up calls for diabetes management and reduces computational complexity and cost.

Copied to clipboard

Arya McCarthy, Hao Zhang, Shankar Kumar, Felix Stahlberg, Ke Wu

A Joint Model for Document Segmentation and Segment Labeling (2020.acl-main)

Challenge:	a challenge in speech translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations.
Approach:	They propose a large language model to split long ASR transcripts into segments that can be independently translated to maximize translation quality.
Outcome:	The proposed model improves the average BLEU by 2.9 points for English–German, English–Spanish, and English–Arabic TED talk translation in 9 sets.

Copied to clipboard

Joe Barrow, Rajiv Jain, Vlad Morariu, Varun Manjunatha, Douglas Oard, Philip Resnik

SynJax: Structured Probability Distributions for JAX (2023.emnlp-demo)

Challenge:	Existing approaches to text segmentation focus on document segmentation and segment labeling separately.
Approach:	They propose a method for jointly segmenting a document and labeling segments . they show that S-LSTM reduces segmentation error by 30% on average .
Outcome:	The proposed method reduces segmentation error by 30% while improving segment labeling.

Copied to clipboard

Miloš Stanojević, Laurent Sartran

Challenge:	a number of deep learning libraries have been developed to account for structured objects . a vectorized implementation of inference algorithms for structured distributions is difficult to implement .
Approach:	SynJax provides vectorized implementations of inference algorithms for structured distributions . authors propose to use a vectorized version of the algorithms to model structure in data . similar structures appear in biology and chemistry .
Outcome:	SynJax provides an efficient vectorized implementation of inference algorithms for structured distributions.

Chinese Content Scoring: Open-Access Datasets and Features on Different Segmentation Levels (2020.aacl-main)

Copied to clipboard

Yuning Ding, Andrea Horbach, Torsten Zesch

Challenge:	Unlike English, which uses spaces as natural separators between words, segmentation of Chinese texts into tokens is challenging.
Approach:	They present two data sets for Chinese content scoring that use Chinese short answer questions and a new scoring system that uses Chinese short-answer questions.
Outcome:	The proposed system performs better on lower segmentation levels than on token level.

Abstract Visual Reasoning with Tangram Shapes (2022.emnlp-main)

Copied to clipboard

Anya Ji, Noriyuki Kojima, Noah Rush, Alane Suhr, Wai Keen Vong, Robert Hawkins, Yoav Artzi

Probabilistic Bilingual Subword Segmentation with Latent Subword Alignment (2026.eacl-srw)

Challenge:	We use tangrams as stimuli in cognitive science to study abstract visual reasoning . pre-trained weights demonstrate limited abstract reasoning, we observe .
Approach:	They propose a resource for studying abstract visual reasoning in humans and machines . they use tangram puzzles as stimuli to create an annotated dataset with >1k distinct stimuli .
Outcome:	The proposed resource is visually and linguistically richer than previous resources . pre-trained weights demonstrate limited abstract reasoning, the authors note .

Copied to clipboard

Shoto Nishida, Daiki Matsui, Takashi Ninomiya, Isao Goto, Akihiro Tamura

Tokenization Is More Than Compression (2024.emnlp-main)

Challenge:	Existing methods do not consider parallel relationships, preventing translation model training.
Approach:	They propose a method for learning subword correspondences in parallel sentence pairs using the EM algorithm.
Outcome:	The proposed method improves translation accuracy for many tasks.

Copied to clipboard

Craig Schmidt, Varshini Reddy, Haoran Zhang, Alec Alameddine, Omri Uzan, Yuval Pinter, Chris Tanner

PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding (2020.findings-emnlp)

Challenge:	Existing tokenization approaches like Byte-Pair Encoding (BPE) have been suggested that their effectiveness stems from their ability to condense text into a relatively small number of tokens.
Approach:	They propose a tokenizer that segments a document’s text into the minimum number of tokens for a given vocabulary and propose fewer tokens to improve downstream performance.
Outcome:	The proposed tokenizers can initialize vocabulary construction and pre-tokenization, and the results show that fewer tokens lead to better performance.

Copied to clipboard

Zhao Jinman, Shawn Zhong, Xiaomin Zhang, Yingyu Liang

CBAL: Context-Based Agentic Learning for Speaker Diarization Segmentation Refinement (2026.acl-srw)

Challenge:	Existing word embeddings assume fixed finite-size vocabularies, hindering their ability to provide useful word representations for out-of-vocaulary words.
Approach:	They propose a model that generalizes word embeddings without extra contextual information . they use the spellings of words to model subword segmentation and compute subword-based compositional word embeds.
Outcome:	The proposed model can generate meaningful subword segmentations without any source of explicit morphological knowledge.

Copied to clipboard

Odwitiyo Dutta, Dinesh K Vishwakarma

Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST Corpora (2022.aacl-short)

Challenge:	Speaker diarization systems produce segmentation errors that degrade transcript readability and downstream applications.
Approach:	They propose a framework that refines segmentation boundaries in diarized scripts . they use a lightweight LLM agent to reason about merge decisions .
Outcome:	The proposed framework achieves 93.4% accuracy across 359 applied merges and reduces segment count by 6.1%.

Copied to clipboard

Sara Papi, Alina Karakanta, Matteo Negri, Marco Turchi

How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology? (2021.findings-emnlp)

Challenge:	Existing models for subtitling require parallel data paired with audio inputs and textual translations.
Approach:	They propose to convert existing ST corpora into SubST resources without human intervention by exploiting audio and text in a multimodal fashion.
Outcome:	The proposed model achieves high segmentation quality in zero-shot conditions with manual and automatic segmentation.

Copied to clipboard

Chantal Amrhein, Rico Sennrich

A Japanese Word Segmentation Proposal (P19-2)

Challenge:	Data-driven subword segmentation is the default strategy for open-vocabulary machine translation but may not be sufficiently generic for learning non-concatenative morphology.
Approach:	They propose to test data-driven subword segmentation on non-concatenative morphological phenomena in a controlled, semi-synthetic setting.
Outcome:	The proposed model can translate non-concatenative morphological phenomena in a controlled, semi-synthetic setting.

Copied to clipboard

Stalin Aguirre, Josafá Aguiar

A Neural CRF-based Hierarchical Approach for Linear Text Segmentation (2023.findings-eacl)

Challenge:	Current word segmentation methods may produce different segmentations for the same strings . this occurs when strings appear in different sentences .
Approach:	They propose to use Japanese word segmentation methods that use a morpheme-based approach to produce different segmentations for the same strings.
Outcome:	The proposed method produces much more consistent segmentation than the current morpheme-based one.

Copied to clipboard

Inderjeet Nair, Aparna Garimella, Balaji Vasan Srinivasan, Natwar Modani, Niyati Chhaya, Srikrishna Karanam, Sumit Shekhar

Unsupervised Subtitle Segmentation with Masked Language Models (2023.acl-short)

Challenge:	Existing methods to segment unformatted text and transcripts explicitly train to predict segment boundaries, but they fail to provide a large annotated dataset.
Approach:	They propose a method to generate hierarchical segmentation structures based on Wikipedia annotations by using a neural conditional random field.
Outcome:	The proposed method outperforms or achieves competitive performance when compared to previous state-of-the-art algorithms.

Copied to clipboard

David Ponce, Thierry Etchegoyhen, Victor Ruiz

Language Models

Challenge:	Existing methods to improve subtitle segmentation are based on character counting and linguistically correct segmentation.
Approach:	They propose a method where subtitle breaks are predicted according to likelihood of punctuation . their approach is highly portable across languages and domains .
Outcome:	The proposed method obtained competitive results in terms of segmentation accuracy across metrics while also fully preserving the original text and complying with length constraints.

Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders (2025.coling-industry)

Copied to clipboard

Saeed Abbasi, Aijun An, Heidar Davoudi, Ron Di Carlantonio, Gary Farmaner

What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition (2021.tacl-1)

Challenge:	Using overlapping text sequences and position-aware weighting, we achieve up to a 10% increase in segmentation F1 score compared to existing methods.
Approach:	They propose a Transformer-based method for document segmentation that utilizes overlapping text sequences with a unique position-aware weighting mechanism to enhance segmentation accuracy.
Outcome:	The proposed method achieves up to 10% increase in segmentation F1 score compared to existing methods and improves quality of generated responses by 5% while achieving four times greater efficiency.

Copied to clipboard

Piotr Żelasko, Raghavendra Pappagari, Najim Dehak

Dialogue Systems & Conversational Agents

Challenge:	Existing punctuation in the transcripts has a massive effect on the models’ performance, and specific label set specificity does not affect dialog act segmentation performance.
Approach:	They apply two pre-trained transformer models to a conversation transcript as a sequence of dialog acts and achieve strong results on Switchboard Dialog Act and Meeting Recorder Dialog Act corpora.
Outcome:	The proposed models achieve 8.4% and 14.2% error rates on the Switchboard Dialog Act and Meeting Recorder Dialog Act corpora.

A Multi-Task Transformer Model for Fine-grained Labelling of Chest X-Ray Reports (2024.lrec-main)

Copied to clipboard

Yuanyi Zhu, Maria Liakata, Giovanni Montana

Information Retrieval

Challenge:	Chest radiography is one of the most commonly performed imaging examinations, with over 50 million chest X-rays annually in the United States . manual review of chest x-ray images can be onerous process prone to errors due to large volumes of images interpreted daily by radiologists .
Approach:	They propose a transformer-based model that segments radiology reports into semantically coherent segments and classifies each segment using a set of 37 radiological abnormalities.
Outcome:	The proposed model achieves state-of-the-art on report segmentation (0.0442 WinDiff) and multi-label classification (0.8 report-level macro F1) over 37 radiological labels and 8 NLP-specific labels.

BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages (2022.findings-acl)

Copied to clipboard

Manuel Mager, Arturo Oncevay, Elisabeth Mager, Katharina Kann, Thang Vu

A Truly Joint Neural Architecture for Segmentation and Parsing (2024.eacl-long)

Challenge:	Morphologically rich polysynthetic languages present a challenge for NLP systems due to data sparsity.
Approach:	They propose to use subword segmentation to reduce data sparsity in polysynthetic languages . they compare supervised and unsupervised morphological segmentation methods to Byte-Pair Encodings .
Outcome:	The proposed methods outperform BPEs in MT tasks for all language pairs except for Nahuatl . the proposed methods are more efficient than supervised methods, but less sparse in fusional languages.

Copied to clipboard

Danit Yshaayahu Levi, Reut Tsarfaty

DE-CLIP: Few-Shot Anomaly Detection via Difference-Guided Embedding Editing (2026.acl-long)

Challenge:	Contemporary multilingual dependency parsers can parse a diverse set of languages, but performance is lower for Morphologically Rich Languages.
Approach:	They propose a joint neural architecture where a lattice-based representation is provided to an arc-factored model and solves the morphological segmentation and syntactic parsing tasks at once.
Outcome:	The proposed architecture is language-agnostic and language-based to improve on Hebrew . it shows that the proposed model can parse morphological segmentation and syntactic parsing tasks at once.

Copied to clipboard

Yage Zhang, Yukun Jiang, Michael Backes, Yang Zhang

Toward Fast and Accurate Neural Discourse Segmentation (D18-1)

Challenge:	Existing approaches to detect anomalies are limited due to the lack of anomalous samples .
Approach:	They propose a framework that edits text embeddings based on the differences between normal and anomalous samples.
Outcome:	The proposed framework achieves 96.6% and 96.99% AUROC on MVTec datasets.

Copied to clipboard

Yizhong Wang, Sujian Li, Jingfeng Yang

Discourse & Pragmatics

Challenge:	Existing discourse segmenters rely on complicated hand-crafted features and are not practical in actual use.
Approach:	They propose an end-to-end neural segmenter based on BiLSTM-CRF framework that can segment texts fast and accurately using a large corpus.
Outcome:	The proposed model is significantly faster than previous methods while achieving state-of-the-art performance on the RST-DT corpus.

Neural Sequence Segmentation as Determining the Leftmost Segments (2021.naacl-main)

Copied to clipboard

Yangming Li, Lemao Liu, Kaisheng Yao

MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition (2021.acl-long)

Challenge:	Existing methods to segment sentences are mostly at token level, limiting their full potential to capture long-term dependencies.
Approach:	They propose a framework that incrementally segments natural language sentences at segment level.
Outcome:	The proposed framework outperforms baseline methods on syntactic chunking and Chinese part-of-speech tagging datasets.

Copied to clipboard

Shuang Wu, Xiaoning Song, Zhenhua Feng

Towards Universal Segmentations: UniSegments 1.0 (2022.lrec-1)

Challenge:	Named Entity Recognition (NER) is a sequence tagging task that extracts named entities from unstructured text.
Approach:	They propose to integrate Chinese character features with radical-level embedding to improve Chinese NER by integrating Chinese character information.
Outcome:	The proposed method can improve Chinese Named Entity Recognition (NER) on well-known datasets.

Copied to clipboard

Zdeněk Žabokrtský, Niyati Bafna, Jan Bodnár, Lukáš Kyjánek, Emil Svoboda, Magda Ševčíková, Jonáš Vidra

SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space (2026.eacl-long)

Challenge:	Existing data resources for morphological segmentation are limited to 32 languages . a large number of word forms exist, with some sub-parts being "recycled" many times .
Approach:	They propose a multilingual data resource for morphological segmentation in 32 languages . they analyze diversity of how individual linguistic phenomena are captured across them .
Outcome:	The proposed scheme is based on 17 existing data resources relevant for segmentation in 32 languages.

Copied to clipboard

Viktoriia Zinkovich, Anton Antonov, Andrei Spiridonov, Denis Shepelev, Andrey Moskalenko, Daria Pugacheva, Elena Tutubalina, Andrey Kuznetsov, Vlad Shakhuro

Robustness in NLP

Challenge:	Existing work on semantically equivalent textual paraphrases has focused on perturbing image inputs.
Approach:	They propose a novel adversarial paraphrasing task that generates grammatically correct paraphrases that sighed the original query meaning while degrading segmentation performance.
Outcome:	The proposed task outperforms previous methods by up to 2x on ReasonSeg and LLMSeg-40k datasets.

RST Parsing from Scratch (2021.naacl-main)

Copied to clipboard

Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, Xiaoli Li

Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision (2021.emnlp-main)

Challenge:	Fig. 1 shows a document level discourse parser that performs top-down end-to-end parsing without requiring segmentation .
Approach:	They propose a top-down end-to-end formulation of document level discourse parsing in the Rhetorical Structure Theory framework.
Outcome:	The proposed model outperforms existing methods in end-to-end parsing and parse with gold segmentation without handcrafted features.

Copied to clipboard

Mieradilijiang Maimaiti, Yang Liu, Yuanhang Zheng, Gang Chen, Kaiyu Huang, Ji Zhang, Huanbo Luan, Maosong Sun

Stochastic Tokenization with a Language Model for Neural Text Classification (P19-1)

Challenge:	Recent state-of-the-art (SOTA) effective neural network methods have been used in Chinese word segmentation (CWS) However, the robustness of the previous neural methods is limited by the large-scale annotated corpus.
Approach:	They propose a self-supervised Chinese word segmentation approach with a straightforward and effective architecture.
Outcome:	The proposed approach outperforms previous methods on 9 different CWS datasets with single criterion training and multiple criteria training and achieves better robustness.

Copied to clipboard

Tatsuya Hiraoka, Hiroyuki Shindo, Yuji Matsumoto

Information Retrieval

Challenge:	Sentences segmented with words or subwords can be difficult to perform text classification tasks.
Approach:	They propose a method to learn tokenization and text classification simultaneously to address these problems.
Outcome:	The proposed method improves on sentiment analysis in Japanese and Chinese using tokenization and text classification models.

Overcoming both Domain Shift and Label Shift for Referring Video Segmentation (2025.findings-naacl)

Copied to clipboard

Hai Huang, Sashuai Zhou, Yan Xia

Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation (2023.findings-acl)

Challenge:	Existing methods to improve the robustness of open-set domain generalization can only recognize seen objects and mark all unseen objects as “unknown” categories .
Approach:	They propose a method to make the model maintain good segmentation ability for unknown objects . they propose CLIP-based Reasoning Prompt which can combine text and visual prompts .
Outcome:	The proposed method can bridge the gap caused by label shift by combining text and visual prompts to improve text-object matching ability.

Copied to clipboard

Francois Meyer, Jan Buys

QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech Corpus (2021.acl-long)

Challenge:	Subword segmenters are used in neural machine translation, but are not used in high-resource settings.
Approach:	They propose a subword segmental machine translation (SSMT) that unifies subword and MT in a single trainable model.
Outcome:	The proposed model improves chrF scores for morphologically rich agglutinative languages and is more robust on a test set constructed for evaluating morphology generalisations.

Copied to clipboard

Hamdy Mubarak, Amir Hussein, Shammur Absar Chowdhury, Ahmed Ali

Learning Adaptive Segmentation Policy for Simultaneous Translation (2020.emnlp-main)

Challenge:	QASR is the largest transcribed Arabic speech corpus in the broadcast domain.
Approach:	They introduce the largest transcribed Arabic speech corpus, QASR, collected from the broadcast domain.
Outcome:	The proposed dataset contains 2,000 hours of speech sampled at 16kHz crawled from Aljazeera news channel.

Copied to clipboard

Ruiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu, Haifeng Wang

Language-Mediated, Object-Centric Representation Learning (2021.findings-acl)

Challenge:	Experimental results show that adaptive segmentation policies for simultaneous translation are more accurate than current methods . if translation starts before adequate source content is delivered, the quality of translation degrades . waiting for too much source text increases latency, which would hurt accuracy .
Approach:	They propose a new adaptive segmentation policy for simultaneous translation based on human interpreters . it learns to segment the source text by considering possible translations produced by the translation model .
Outcome:	Experimental results show that the proposed method achieves better accuracy-latency trade-off over state-of-the-art methods.

Copied to clipboard

Ruocheng Wang, Jiayuan Mao, Samuel Gershman, Jiajun Wu

Representation Learning

Challenge:	Recent work has studied the problem of unsupervised object representation learning, though without language.
Approach:	They propose language-mediated, Objectcentric Representation Learning (LORL) a paradigm for learning disentangled, objectcentric scene representations from vision and language.
Outcome:	The proposed paradigm improves performance of unsupervised object discovery algorithms on two datasets using language.

Movie Plot Analysis via Turning Point Identification (D19-1)

Copied to clipboard

Pinelopi Papalampidi, Frank Keller, Mirella Lapata

Challenge:	Using computational literary analysis, we analyze novels, plays, and screenplays for their turning points.
Approach:	They propose to use turning points to analyze screenplays and plot synopses as tools for analysis . they propose to build a neural network model that identifies turning points in plot synoopse .
Outcome:	The proposed model outperforms baselines based on state-of-the-art sentence representations and expected position of turning points.

A Pragmatic Approach for Classical Chinese Word Segmentation (L18-1)

Copied to clipboard

Shilei Huang, Jiangqin Wu

A Language Model-based Generative Classifier for Sentence-level Discourse Parsing (2021.emnlp-main)

Challenge:	Classical Chinese word segmentation is largely neglected due to its obsoleteness . a new approach to segmentation using a marked-up corpus is needed .
Approach:	They propose a pragmatic approach to deal with Classical Chinese word segmentation without any marked-up corpus.
Outcome:	The proposed method makes the CCWS without any marked-up corpus more accurate compared with collocation-based methods.

Copied to clipboard

Ying Zhang, Hidetaka Kamigaito, Manabu Okumura

A Reference-free Segmentation Quality Index (SegReFree) (2023.findings-emnlp)

Challenge:	Existing methods to consider textual coherence are limited in labeled data.
Approach:	They propose a language model-based generative classifier that uses labels as input and embeds labels into their representations.
Outcome:	The proposed classifier achieves state-of-the-art in discourse segmentation and relation F1 scores with gold boundaries and automatically segmented boundaries.

Copied to clipboard

Evan Lucas, Dylan Kangas, Timothy Havens

Challenge:	Topic segmentation is the process of finding boundaries in sentences that separate groups of adjacent sentences at shifts in semantic meaning.
Approach:	They propose a reference-free segmentation quality index to assess segmentation . metric uses a modified cluster validity metric with semantic embeddings of the sentences .
Outcome:	The proposed metric uses a modified cluster validity metric with semantic embeddings of the sentences to determine the quality of the segmentation.

SBAAM! Eliminating Transcript Dependency in Automatic Subtitling (2024.acl-long)

Copied to clipboard

Marco Gaido, Sara Papi, Matteo Negri, Mauro Cettolo, Luisa Bentivogli

Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning (2024.naacl-long)

Challenge:	Subtitling is a crucial task for enhancing the accessibility of audiovisual content and relying on automatic transcripts for the three subtasks is uncharted territory.
Approach:	They propose a model capable of producing automatic subtitles, completely eliminating any dependence on intermediate transcripts also for timestamp prediction.
Outcome:	Experimental results show that the proposed model eliminates the need for intermediate transcripts for timestamp prediction across multiple language pairs and diverse conditions.

Copied to clipboard

Kazuma Hashimoto, Karthik Raman, Michael Bendersky

Low-Resource NLP

Challenge:	Recent advances of Large Language Models (LLMs) have been pushing the field of Natural Language Processing (NLP) to the next level in many different aspects.
Approach:	They propose a novel labeling method which estimates how much incremental knowledge is brought into LLMs by a demonstration.
Outcome:	The proposed method estimates how much incremental knowledge is brought into the LLMs by a demonstration.

Learning to Segment Actions from Observation and Narration (2020.acl-main)

Copied to clipboard

Daniel Fried, Jean-Baptiste Alayrac, Phil Blunsom, Chris Dyer, Stephen Clark, Aida Nematzadeh

Visual Data in NLP

Challenge:	a generative segmental model of task structure is applied to video training . despite its simplicity, the model performs well in unsupervised and weakly-supervised settings .
Approach:	They propose a generative segmental model of task structure guided by narration to video segmentation .
Outcome:	The proposed model performs well in unsupervised and weakly-supervised training . it allows us to vary the sources of supervision used in training despite its simplicity .

C-HTS: A Concept-based Hierarchical Text Segmentation approach (L18-1)

Copied to clipboard

Mostafa Bayomi, Séamus Lawless

Multi-task Pairwise Neural Ranking for Hashtag Segmentation (P19-1)

Challenge:	Existing approaches to hierarchical text segmentation use lexical and/or syntactic similarity to identify the coherent segments of text.
Approach:	They propose a Concept-based Hierarchical Text Segmentation approach that uses the semantic relatedness between text constituents to represent meaning.
Outcome:	The proposed method performs well on two publicly available datasets.

Copied to clipboard

Mounica Maddela, Wei Xu, Daniel Preoţiuc-Pietro

Low-Resource NLP

Challenge:	Hashtags are used to add metadata to textual utterances, but their semantic content is difficult to infer as they often contain multiple tokens joined together.
Approach:	They propose to use a dataset of 12,594 hashtags to infer hashtag semantics . they propose to frame the problem as a pairwise ranking problem between candidate segmentations .
Outcome:	The proposed methods show 24.6% error reduction in hashtag segmentation accuracy compared to the current state-of-the-art method.

Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text (2023.eacl-main)

Copied to clipboard

Marwa Gaser, Manuel Mager, Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu

Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert Domains (P19-1)

Challenge:	Code-switching (CS) is a problem in machine translation, but its performance is not investigated for CS settings.
Approach:	They propose to use morphological segmentation techniques for machine translation tasks . they compare morphology-based and frequency-based segmentation for MT tasks based on data size .
Outcome:	The proposed approach performs best in MT tasks but under-performs in other languages.

Copied to clipboard

Claudia Schulz, Christian M. Meyer, Jan Kiesewetter, Michael Sailer, Elisabeth Bauer, Martin R. Fischer, Frank Fischer, Iryna Gurevych

Challenge:	Existing deep learning methods require large amounts of training data to achieve reasonable performance.
Approach:	They propose to generate automatic annotation suggestions for a discourse-level sequence labelling task that requires extensive domain expertise.
Outcome:	The proposed model improves with newly annotated texts while introducing no biases.

MRL Parsing Without Tears: The Case of Hebrew (2024.findings-acl)

Copied to clipboard

Shaltiel Shmidman, Avi Shmidman, Moshe Koppel, Reut Tsarfaty

Information Extraction & Text Mining

Challenge:	a new approach to parsing morphologically rich languages (MRLs) is needed to overcome the deficiencies of current approaches.
Approach:	They propose a "flipped pipeline" where multiple layers are predicted independently on whole-token basis and then synthesized.
Outcome:	The proposed model achieves near-SOTA performance on Hebrew NLP tasks.

Shrinking Japanese Morphological Analyzers With Neural Networks and Semi-supervised Learning (N19-1)

Copied to clipboard

Arseny Tolmachev, Daisuke Kawahara, Sadao Kurohashi

Improving Segmentation for Technical Support Problems (2020.acl-main)

Challenge:	Modern neural morphological analyzers consume gigabytes of memory.
Approach:	They propose a method which uses unigram character embeddings to train a model on labels produced by a state-of-the-art analyzer.
Outcome:	The proposed model outperforms dictionary-based methods in Japanese and Chinese . it uses less than 15 megabytes of space and is much smaller than the dictionary- based one .

Copied to clipboard

Kushal Chauhan, Abhirut Gupta

Neural Transition Based Parsing of Web Queries: An Entity Based Approach (D18-1)

Challenge:	Technical support problems are long and complex and cannot be correctly parsed by tools designed for natural language.
Approach:	They propose a sequence labelling task and a supervised text segmentation approach to solve this problem.
Outcome:	The proposed approach improves on the downstream task of answer retrieval.

Copied to clipboard

Rivka Malca, Roi Reichart

A Second Wave of UD Hebrew Treebanking and Cross-Domain Parsing (2022.emnlp-main)

Challenge:	Existing query parsers that account for the unique grammar of web queries rely on resources not available outside of big web corporations.
Approach:	They propose a biLSTM query parser that explicitly accounts for the unique grammar of queries.
Outcome:	The proposed query parser outperforms existing state-of-the-art parsers on 2500 annotated queries.

Copied to clipboard

Amir Zeldes, Nick Howell, Noam Ordan, Yifat Ben Moshe

Compositional Reasoning via Joint Image and Language Decomposition (2026.findings-eacl)

Challenge:	Foundational Hebrew NLP tasks have relied on various versions of the Hebrew Treebank . however, the data in the HTB is now over 30 years old and does not cover many aspects of contemporary Hebrew on the web.
Approach:	They propose to use Hebrew Wikipedia to stratify the text from a UD treebank.
Outcome:	The proposed treebank is based on a single-source newswire corpus selected from Hebrew Wikipedia.

Copied to clipboard

Dwip Dalal, Madhav Kanda, Zhenhailong Wang, Heng Ji, Unnat Jain

What the DAAM: Interpreting Stable Diffusion Using Cross Attention (2023.acl-long)

Challenge:	Existing approaches typically decompose only language queries, treating images as monolithic inputs.
Approach:	They propose a framework that decomposes both images and questions into visual sub-domains with corresponding sub-questions.
Outcome:	REDI achieves absolute accuracy improvements of 8.9%, 8.2%, and 16.0% over existing models.

Copied to clipboard

Raphael Tang, Linqing Liu, Akshat Pandey, Zhiying Jiang, Gefei Yang, Karun Kumar, Pontus Stenetorp, Jimmy Lin, Ferhan Ture

How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation (2021.findings-acl)

Challenge:	a new text-image attribution analysis model for text-to-image generation is understudied due to ethical constraints . corporators have restricted the general public from using the models and their weights .
Approach:	They perform a text-image attribution analysis on Stable Diffusion, a recently open-sourced model.
Outcome:	The proposed method achieves a competitive 58.8-64.8 mIoU on noun segmentation and fair to good mean opinion scores on all parts of speech rated by humans . it also achieves good attribution quality on all part of speech, rated in humans - and the first to interpret large diffusion models from a visuolinguistic perspective.

Copied to clipboard

Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi

Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention (2020.acl-main)

Challenge:	Existing methods for subword splitting penalize the representation of feminine linguistic markings.
Approach:	They propose a method that preserves subword splitting while leveraging character-based segmentation to properly translate gender.
Outcome:	The proposed approach preserves BPE overall translation quality while leveraging the higher ability of character-based segmentation to properly translate gender.

Copied to clipboard

Yanzeng Li, Bowen Yu, Xue Mengge, Tingwen Liu

Attention Is All You Need for Chinese Word Segmentation (2020.emnlp-main)

Challenge:	Pre-trained Chinese language models take character as the basic unit and learn representation according to character’s external contexts, ignoring the semantics expressed in the word, which is the smallest meaningful utterance in Chinese.
Approach:	They propose to pool character-level attention to the word level and propose to alleviate the potential issue of segmentation error propagation by multi-source information fusion.
Outcome:	The proposed approach improves on five Chinese NLP benchmark tasks against BERT, ERNIE and BERT-wwm.

Copied to clipboard

Sufeng Duan, Hai Zhao

Language Models

Challenge:	Recent work on Chinese word segmentation has been concerned about the following three perspectives.
Approach:	They propose to use a greedy decoding algorithm to improve Chinese word segmentation model.
Outcome:	The proposed model achieves state-of-the-art or comparable performance against strong baselines in strict closed test setting.

A Joint Multiple Criteria Model in Transfer Learning for Cross-domain Chinese Word Segmentation (2020.emnlp-main)

Copied to clipboard

Kaiyu Huang, Degen Huang, Zhuang Liu, Fengran Mo

DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution (2026.findings-eacl)

Challenge:	Existing methods for word-level segmentation (CWS) for the Chinese language have been successful in large-scale annotated corpora.
Approach:	They propose a method that integrates different segmentation criteria into one model . they use a transfer learning method to improve the performance of OOV words .
Outcome:	The proposed method achieves state-of-the-art performance on multiple benchmark datasets . it shows a competitive practicability and generalization ability for the CWS task .

Copied to clipboard

L. D. M. S. Sai Teja, N. Siva Gopala Krishna, Ufaq Khan, Muhammad Haris Khan, Atul Mishra

Evaluating Subtitle Segmentation for End-to-end Generation Systems (2022.lrec-1)

Challenge:	a new framework for mixed authorship detection addresses the challenge of segmenting mixed-authorship text . mixed-authored text detection is a growing concern in the age of advanced large language models . a recent survey highlighted the greater challenges of detecting AI content in realworld settings .
Approach:	They propose a framework for mixed authorship detection that integrates stylometric cues, perplexity-driven signals, and structured boundary modeling to accurately segment collaborative human-AI content.
Outcome:	The proposed framework improves robustness against adversarial perturbations while revealing limitations.

Copied to clipboard

Alina Karakanta, François Buet, Mauro Cettolo, François Yvon

Challenge:	Subtitle segmentation can be evaluated with sequence segmentation metrics against a human reference, but cannot be applied when systems generate outputs different than the reference, e.g. with end-to-end subtitling systems.
Approach:	They propose to use Sigma to evaluate subtitle segmentation against a human reference and a boundary projection method to disentangle the effect of good segmentation from text quality.
Outcome:	The proposed method disentangles the effect of good segmentation from text quality and is compared with existing metrics.

Revisiting Syllables in Language Modelling and Their Application on Low-Resource Machine Translation (2022.coling-1)

Copied to clipboard

Arturo Oncevay, Kervy Dante Rivas Rojas, Liz Karen Chavez Sanchez, Roberto Zariquiey

VCSUM: A Versatile Chinese Meeting Summarization Dataset (2023.findings-acl)

Challenge:	Language modelling and machine translation tasks mostly use subword or character inputs, but syllables are rarely used.
Approach:	They explore the potential of syllables for open-vocabulary language modelling in 21 languages.
Outcome:	The proposed method outperforms characters and subwords in a non-related and low-resource language pair.

Copied to clipboard

Han Wu, Mingjie Zhan, Haochen Tan, Zhaohui Hou, Ding Liang, Linqi Song

Text Segmentation by Cross Segment Attention (2020.emnlp-main)

Challenge:	Compared to news and chat summarization, meeting summarizing is decelerated by the limited data.
Approach:	They propose a Chinese meeting summarization dataset that provides annotations for each transcript and a set of benchmark models to facilitate further research.
Outcome:	The proposed model can be used to summarize the content of meeting transcripts in Chinese.

Copied to clipboard

Michal Lukasik, Boris Dadachev, Kishore Papineni, Gonçalo Simões

Text Segmentation

Challenge:	Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents.
Approach:	They propose three transformer-based NLP models that break up text into constituents and compare them to previous approaches.
Outcome:	The proposed architectures reduce errors by a large margin on three datasets and improve performance on real-world datasets.

Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability (2021.findings-acl)

Copied to clipboard

Kaiyu Huang, Junpeng Liu, Degen Huang, Deyi Xiong, Zhuang Liu, Jinsong Su

Is Word Segmentation Child’s Play in All Languages? (P19-1)

Challenge:	Pre-trained language models alleviate segmentation ambiguity and out-of-vocabulary (OOV) words.
Approach:	They propose a semisupervised neural method which distills knowledge from unlabeled data to a student model to improve both in-domain and out-of-domain CWS.
Outcome:	The proposed method can keep practicability of the lightweight student model and improve segmentation effectively on downstream Chinese NLP tasks.

Copied to clipboard

Georgia R. Loukatou, Steven Moran, Damian Blasi, Sabine Stoll, Alejandrina Cristia

A Pointer Network Architecture for Joint Morphological Segmentation and Tagging (2020.findings-emnlp)

Challenge:	Existing word learning strategies for infants are cross-linguistically robust . infants do not know which language(s) will be found in their environment at the beginning of development .
Approach:	They propose to use 11 conceptually diverse algorithms to learn word-like units in infants . they propose to employ cross-linguistically robust algorithms that can be used by all infants.
Outcome:	The proposed algorithms perform above chance on 8 different languages . the results show that some of the algorithms are cross-linguistically valid .

Copied to clipboard

Amit Seker, Reut Tsarfaty

Where’s the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence Segmentation (2023.acl-long)

Challenge:	Morphological Disambiguation (MD) is a task of decomposing tokens into morphemes . a simple pipeline is used to segment and tagging raw tokens .
Approach:	They propose a new pointer network model that combines symbolic knowledge of morphemes with the learning capacity of neural end-to-end modeling.
Outcome:	The proposed model outperforms all previous reported results on Hebrew and Turkish . it uses morphological knowledge and the learning capacity of neural end-to-end modeling .

Copied to clipboard

Benjamin Minixhofer, Jonas Pfeiffer, Ivan Vulić

Incorporating Inner-word and Out-word Features for Mongolian Morphological Segmentation (2020.coling-main)

Challenge:	Prior sentence segmentation tools rely on punctuation or require a large amount of training data . a new method for multilingual sentence segmenting is proposed to replace the best prior tools by using only sentence-segmented examples.
Approach:	They propose a punctuation-agnostic sentence segmentation method that uses newline characters which implicitly perform segmentation into paragraphs.
Outcome:	The proposed method outperforms all prior best sentence segmentation tools by 6.1% F1 points.

Copied to clipboard

Na Liu, Xiangdong Su, Haoran Zhang, Guanglai Gao, Feilong Bao

Lexically Grounded Subword Segmentation (2024.emnlp-main)

Challenge:	Mongolian morphological segmentation is a crucial preprocessing step in many Mongolian related NLP applications.
Approach:	They propose a neural network incorporating inner-word and out-word features for Mongolian morphological segmentation.
Outcome:	The proposed network is compared with baselines and evaluates its performance.

Copied to clipboard

Jindřich Libovický, Jindřich Helcl

Developing a Rhetorical Structure Theory Treebank for Czech (2024.lrec-main)

Challenge:	Statistical word segmentation algorithms have remained a thorn in the side of many researchers.
Approach:	They propose to use unsupervised morphological analysis with Morfessor as pre-tokenization and an algebraic method for obtaining subword embeddings grounded in a word embeddable space.
Outcome:	The proposed methods improve morphological plausibility and Rényi efficiency on part-of-speech tagging and machine translation tasks.

Copied to clipboard

Lucie Polakova, Jiří Mírovský, Šárka Zikánová, Eva Hajicova

Linguistic Theories

Challenge:	a paper on the Czech RST Discourse Treebank is the first version of a textual annotation system based on the Rhetorical Structure Theory . document is annotated using the RST, a global coherence model proposed by Mann and Thompson .
Approach:	They introduce the first version of the Czech RST Discourse Treebank . paper presents an annotation process and provides corpus statistics and evaluation .
Outcome:	The paper presents the first version of the Czech RST Discourse Treebank . the treebank includes two gold annotations representing divergent interpretations .

DISRPT: A Multilingual, Multi-domain, Cross-framework Benchmark for Discourse Processing (2024.lrec-main)

Copied to clipboard

Chloé Braud, Amir Zeldes, Laura Rivière, Yang Janet Liu, Philippe Muller, Damien Sileo, Tatsuya Aoyama

Text Classification

Challenge:	DISRPT is a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing.
Approach:	They present a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing that includes 13 languages and 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks.
Outcome:	The DISRPT dataset includes data from 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks.

A Conditional Splitting Framework for Efficient Constituency Parsing (2021.acl-long)

Copied to clipboard

Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, Xiaoli Li

Topical Segmentation of Spoken Narratives: A Test Case on Holocaust Survivor Testimonies (2022.emnlp-main)

Challenge:	Developing efficient and effective parsing solutions has always been a key focus in NLP.
Approach:	They propose a generic seq2seq parsing framework that casts constituency parsers into a series of conditional splitting decisions.
Outcome:	The proposed framework outperforms state-of-the-art (SoTA) methods in discourse parsing . it is based on a syntactic and discourse parsed model and is linear in number of nodes .

Copied to clipboard

Eitan Wagner, Renana Keydar, Amit Pinchevski, Omri Abend

Word Order Does Matter and Shuffled Language Models Know It (2022.acl-long)

Challenge:	Topical segmentation is a task that has been neglected in recent work . a drawback of this approach is the lack of interpretability, which is crucial in some contexts.
Approach:	They propose to model running (spoken) narratives using topic segmentation . they hypothesize that boundary points between segments correspond to low mutual information .
Outcome:	The proposed approaches show significant improvements over manual approaches.

Copied to clipboard

Mostafa Abdou, Vinit Ravishankar, Artur Kulmizev, Anders Søgaard

LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)

Challenge:	Recent studies have shown that language models pretrained and/or fine-tuned on randomly permuted sentences exhibit competitive performance on GLUE, putting into question the importance of word order information.
Approach:	They propose a transformer-based BERT architecture that uses a fixed, sinusoidal position embedding added to each token embeddable to compensate for this absence of linear order.
Outcome:	The proposed model retains word order information because of the dependencies between sentence length and unigram probabilities.

Copied to clipboard

Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li

End-to-End Simultaneous Speech Translation with Differentiable Segmentation (2023.findings-acl)

Challenge:	Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS).
Approach:	They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning.
Outcome:	The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks.

Copied to clipboard

Shaolei Zhang, Yang Feng

Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning (2020.lrec-1)

Challenge:	Existing methods to perform simultaneous speech translation always separate segmentation from the underlying model.
Approach:	They propose to use Differentiable Segmentation (DiSeg) to learn segmentation from the translation model.
Outcome:	Experimental results show that the proposed model can learn segmentation from the translation model.

Copied to clipboard

Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo

Morphological Segmentation for Low Resource Languages (2020.lrec-1)

Challenge:	Subword segmentation is a standard preprocessing step in many neural approaches to natural language processing.
Approach:	They propose to train a unigram subword model using a recursive algorithm and lexicon pruning algorithm.
Outcome:	The proposed method improves on the original training algorithm and improves morphological segmentation accuracy.

Copied to clipboard

Justin Mott, Ann Bies, Stephanie Strassel, Jordan Kodner, Caitlin Richter, Hongzhi Xu, Mitchell Marcus

Automating Idea Unit Segmentation and Alignment for Assessing Reading Comprehension via Summary Protocol Analysis (2022.lrec-1)

Challenge:	a new corpus of annotated morphological data is described for the DARPA LORELEI Program . the data is annotating 9 low resource languages and root information for 7 of the languages .
Approach:	This paper describes a new morphology resource created by Linguistic Data Consortium and the University of Pennsylvania for the DARPA LORELEI Program.
Outcome:	The annotated corpus provides a gold standard for unsupervised morphological segmenters and analyzers . the language-specific annotation guidelines were language-independent, but included morphology paradigms and other specifications.

Copied to clipboard

Marcello Gecchele, Hiroaki Yamada, Takenobu Tokunaga, Yasuyo Sawaki, Mika Ishizuka

Reasoning

Challenge:	In second language learning, summaries are among the most popular type of student assignments.
Approach:	They propose to revise the annotation guidelines to allow machine implementation of the new annotation guidelines.
Outcome:	The proposed algorithm achieves 0.789 precision and 0.844 recall over the L2WS 2021 corpus.

Unsupervised Melody-to-Lyrics Generation (2023.acl-long)

Copied to clipboard

Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Gunnar Sigurdsson, Chenyang Tao, Wenbo Zhao, Tagyoung Chung, Jing Huang, Nanyun Peng

Low-Resource NLP

Challenge:	Existing methods for automatic melody-to-lyric generation are limited due to the limited amount of melody-lyrical aligned data.
Approach:	They propose a method for automatic melody-to-lyric generation without training on any aligned melody-lyr data.
Outcome:	The proposed model generates high-quality lyrics that are singable, intelligible, and coherent than baseline models.

The Norwegian Dialect Corpus Treebank (2022.lrec-1)

Copied to clipboard

Andre Kåsen, Kristin Hagen, Anders Nøklestad, Joel Priestly, Per Erik Solberg, Dag Trygve Truslew Haug

ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English (2020.lrec-1)

Challenge:	The NDC Treebank consists of recordings made between 2006 and 2012 and is annotated with morphological and syntactic information.
Approach:	They present the NDC Treebank of spoken Norwegian dialects in the Bokml variety of Norwegian.
Outcome:	The treebank consists of 4587 speech segments, overall 66009 tokens, from 17 different Norwegian dialects from south, west, east and north of Norway.

Copied to clipboard

Injy Hamed, Ngoc Thang Vu, Slim Abdennadher

Learning Adaptive Segmentation Policy for End-to-End Simultaneous Translation (2022.acl-long)

Challenge:	a corpus of Arabic-English code-switching (CS) spontaneous speech is collected in an Egyptian university soundproof room . the language in Egypt is rather complex and poses many challenges to natural language processing (NLP)
Approach:	They present an Egyptian Arabic-English code-switching (CS) spontaneous speech corpus.
Outcome:	The proposed corpus is designed to be used in automatic speech recognition systems . it provides a useful resource for analyzing the CS phenomenon from linguistic, sociological, and psychological perspectives.

Copied to clipboard

Ruiqing Zhang, Zhongjun He, Hua Wu, Haifeng Wang

Hierarchical Text Segmentation for Medieval Manuscripts (2020.coling-main)

Challenge:	Existing methods to perform simultaneous speech-to-text translation ignore contextual information and suffer from low translation quality.
Approach:	They propose an adaptive segmentation policy for simultaneous speech-to-text translation . it learns to segment the source streaming speech into meaningful units .
Outcome:	The proposed method achieves a good accuracy-latency trade-off over state-of-the-art methods on English-German and Chinese-English.

Copied to clipboard

Amir Hazem, Beatrice Daille, Dominique Stutzmann, Christopher Kermorvant, Louis Chevalier

PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition (2023.findings-acl)

Challenge:	Until now, text segmentation methods have only addressed data sets lying within the scope of narrative and expository texts or user dialogues texts.
Approach:	They propose a bottom-up greedy approach that enhances the results . they argue that books of hours exhibit a complex hierarchical entangled structure .
Outcome:	The proposed bottom-up greedy approach significantly enhances the results.

Copied to clipboard

Sihao Chen, Senaka Buthpitiya, Alex Fabrikant, Dan Roth, Tal Schuster

Reasoning

Challenge:	Existing systems for Natural Language Inference (NLI) only recognize textual entailment relations on sentence-level . however, even a simple sentence often contains multiple propositions, i.e. distinct units of meaning conveyed by the sentence .
Approach:	They propose a system to recognize whether one text is textually entailed by another . they use a corpus of over 45K propositions annotated by human raters to study the textual entailment relation of each proposition in a sentence individually.
Outcome:	The proposed dataset can be used to understand the compositionality of NLI labels.

Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation (2025.emnlp-main)

Copied to clipboard

Enora Rice, Katharina von der Wense, Alexis Palmer

Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation (2024.lrec-main)

Challenge:	despite interest in language documentation, we still lack broadly usable tools that support workflows.
Approach:	They propose to integrate user-centered design principles into NLP to reshape the field.
Outcome:	The proposed model fails to meet core usability needs in real-world language documentation contexts.

Copied to clipboard

Matthias Sperber, Ondřej Bojar, Barry Haddow, Dávid Javorský, Xutai Ma, Matteo Negri, Jan Niehues, Peter Polák, Elizabeth Salesky, Katsuhito Sudoh, Marco Turchi

Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic Segmentation (2025.acl-long)

Challenge:	a meta-analysis of human evaluation for speech translation has not been conducted . noisy data and segmentation mismatches are challenges for automatic metrics .
Approach:	They propose an evaluation strategy based on automatic resegmentation and direct assessment with segment context.
Outcome:	The proposed evaluation strategy is robust and scores well-correlated with other types of human judgements.

Copied to clipboard

Michael S. Yantosca, Albert M. K. Cheng

CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing (L18-1)

Challenge:	Existing approaches to phonetic segmentation are hierarchical and end-to-end . many mistakes in final output stem from subtle segmenter perturbations .
Approach:	They propose a phonetic segmentation system that trains on raw sound files alone . it can modulate computational exactness and reduce acoustic model size, they argue .
Outcome:	The proposed method reduces the size of the acoustic model and training epochs.

Copied to clipboard

Amir More, Özlem Çetinoğlu, Çağrı Çöltekin, Nizar Habash, Benoît Sagot, Djamé Seddah, Dima Taji, Reut Tsarfaty

A Gold Standard Dependency Treebank for Turkish (2020.lrec-1)

Challenge:	Using the universal dependencies framework, we address the need for a universal representation of morphological analysis that can capture alternative morphology of surface tokens and is compatible with the segmentation and morphologic annotation guidelines prescribed for UD treebanks.
Approach:	They propose a new annotation format for word lattices that represent morphological analyses and a resource that obeys this format for a range of typologically different languages.
Outcome:	The proposed model can capture alternative morphological analyses of surface tokens and is compatible with the segmentation and morphology guidelines prescribed for UD treebanks.

Copied to clipboard

Tolga Kayadelen, Adnan Ozturel, Bernd Bohnet

Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence (2020.acl-main)

Challenge:	Currently, Turkish treebanks are limited due to the limited number of annotated sentences in the domains of Wikipedia and ITU Web Treebanks.
Approach:	They propose to annotate Turkish web and Wikipedia sentences for segmentation, morphology, part-of-speech and dependency relations using tagsets and a Wikipedia section.
Outcome:	The proposed treebank is the largest publicly available morpho-syntactic treebank in terms of word count and has a dedicated Wikipedia section.

Copied to clipboard

Xiaoyu Shen, Ernie Chang, Hui Su, Cheng Niu, Dietrich Klakow

Learning to Follow Object-Centric Image Editing Instructions Faithfully (2023.findings-emnlp)

Challenge:	Recent neural attention models conflate all steps into a single end-to-end system and simplify training process.
Approach:	They propose to explicitly segment target text into fragment units and align them with their data correspondences.
Outcome:	The proposed model outperforms neural attention models on E2E and WebNLG benchmarks.

Copied to clipboard

Tuhin Chakrabarty, Kanishk Singh, Arkadiy Saakyan, Smaranda Muresan

Visual Data in NLP

Challenge:	avrahami et al., 2022b,a): natural language instructions are often underspecified, requiring models to uncover their implicit meaning.
Approach:	They propose to use paired data to model the implicit meaning of instructions . they also propose to ground the model to localize where the edit has to be performed .
Outcome:	The proposed model performs better than state-of-the-art baselines on paired data, showing improvements in quality and faithfulness.

Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation (2024.emnlp-main)

Copied to clipboard

Markus Frohmann, Igor Sterner, Ivan Vulić, Benjamin Minixhofer, Markus Schedl

Subword Segmentation in LLMs: Looking at Inflection and Consistency (2024.emnlp-main)

Challenge:	Sentence segmentation is a key task in many NLP systems, but no prior method has achieved all of the features needed to segment a text into sentences.
Approach:	They propose a new model that uses punctuation to enhance robustness and adaptability.
Outcome:	The proposed model outperforms baselines across 8 corpora across diverse domains and languages and is available under the MIT license.

Copied to clipboard

Marion Marco, Alexander Fraser

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing (2021.emnlp-main)

Challenge:	Subword segmentation is not linguistically guided and is not currently well understood in LLMs.
Approach:	They group words according to their segmentation properties and compare how well a model can solve a linguistic task for these groups using two criteria: adherence to morpheme boundaries and segmentation consistency of inflected forms of a lemma.
Outcome:	The results show that the criterion of segmentation consistency can predict the model’s ability to recognize and generate the lemma from an inflected form, providing evidence that subword segmentation is relevant.

Copied to clipboard

Chunchuan Lyu, Shay B. Cohen, Ivan Titov

RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought (2025.acl-long)

Challenge:	Abstract Meaning Representations (AMR) represents sentence meaning as a directed acyclic graph.
Approach:	They propose to treat alignment and segmentation as latent variables and induce them as part of end-to-end training.
Outcome:	The proposed model achieves significant performance gains over a 'greedy' segmentation heuristic.

Copied to clipboard

Yi Lu, Jiawang Cao, Yongliang Wu, Bozheng Li, Licheng Tang, Yangguang Ji, Chong Wu, Jay Wu, Wenbo Zhu

Extended Parallel Corpus for Amharic-English Machine Translation (2022.lrec-1)

Challenge:	Recent advances in multi-modal learning have enhanced MLLMs' ability to reason about visual content.
Approach:	They propose a framework that unifies multi-step multimodal reasoning with grounded visual understanding.
Outcome:	The proposed framework surpasses state-of-the-art methods by +6.5 gIoU and +9.2 cIou on ReasonSeg and achieves 49.7 mAP on SegInW under zero-shot settings.

Copied to clipboard

Andargachew Mekonnen Gezmu, Andreas Nürnberger, Tesfaye Bayu Bati

A State-independent and Time-evolving Network for Early Rumor Detection in Social Media (2020.emnlp-main)

Challenge:	Existing approaches to automate the complex task of translation are tedious and expensive.
Approach:	They describe acquisition, preprocessing, segmentation, and alignment of an Amharic-English parallel corpus.
Outcome:	The proposed corpus outperforms statistical machine translation models by six to seven BLEU points . the results show that the subword models outperformed word-based models by three to four BLUE points compared with the word-base models .

Copied to clipboard

Rui Xia, Kaizhou Xuan, Jianfei Yu

Challenge:	Existing methods to rumor detection ignored dynamical evolution of an event and failed to capture its unique features in different states.
Approach:	They propose a state-independent and time-evolving Network (STN) for rumor detection based on fine-grained event state detection and segmentation.
Outcome:	The proposed framework can significantly improve the rumor detection accuracy in comparison with some strong baseline systems.

Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations (2024.findings-emnlp)

Copied to clipboard

Rose Wang, Pawan Wirawarn, Kenny Lam, Omar Khattab, Dorottya Demszky

HashSet - A Dataset For Hashtag Segmentation (2022.lrec-1)

Challenge:	POSR is a task of breaking down conversations into segments and linking each segment to the relevant reference item.
Approach:	They propose a task that breaks down conversations into segments and links each segment to the relevant reference item.
Outcome:	The proposed method outperforms independent segmentation pipelines and large language models on joint metrics.

Copied to clipboard

Prashant Kodali, Akshala Bhatnagar, Naman Ahuja, Manish Shrivastava, Ponnurangam Kumaraguru

Challenge:	Hashtag segmentation is the task of breaking a hashtag into constituent tokens . hashtags are often written in unique ways, including spelling variations, and special characters.
Approach:	They propose a dataset that breaks hashtags into constituent tokens to train and validate models.
Outcome:	The proposed dataset provides an alternate set of hashtags to build and validate hashtag segmentation models.

Linguistically Motivated Sign Language Segmentation (2023.findings-emnlp)

Copied to clipboard

Amit Moryossef, Zifan Jiang, Mathias Müller, Sarah Ebling, Yoav Goldberg

Seshat: a Tool for Managing and Verifying Annotation Campaigns of Audio Data (2020.lrec-1)

Challenge:	Sign language segmentation is a crucial task in sign language processing systems.
Approach:	They propose to combine two kinds of segmentation: segmentation into individual signs and segmentation to segment into phrases, larger units comprising several signs.
Outcome:	The proposed model is based on linguistic cues observed in sign language corpora and replaces the predominant IO tagging scheme with BIO taging to account for continuous signing.

Copied to clipboard

Hadrien Titeux, Rachid Riad, Xuan-Nga Cao, Nicolas Hamilakis, Kris Madden, Alejandrina Cristia, Anne-Catherine Bachoud-Lévi, Emmanuel Dupoux

Pixel-Level Reasoning Segmentation via Multi-turn Conversations (2025.acl-long)

Challenge:	Seshat is a software for the automated management of annotation campaigns for audio/speech data.
Approach:	They propose a system for the automated management of annotation campaigns for audio/speech data which addresses these challenges.
Outcome:	The proposed system computes an associated inter-annotator agreement with the gamma measure taking into account the categorisation and segmentation discrepancies.

Copied to clipboard

Dexian Cai, Xiaocui Yang, YongKang Liu, Daling Wang, Shi Feng, Yifei Zhang, Soujanya Poria

AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation (2026.acl-long)

Challenge:	Existing visual perception systems focus on region-level segmentation in single-turn dialogues . existing systems cannot reason at the pixel level and comprehend dynamic user intent .
Approach:	They propose a task that tracks evolving user intent via multi-turn interactions for fine-grained segmentation.
Outcome:	The proposed method outperforms existing baselines in segmentation and reasoning metrics.

Copied to clipboard

Rui Qian, Chuanhang Deng, Qiang Huang, Jian Xiong, Mingxuan Li, Yingbo Zhou, Wei Zhai, Jintao Chen, Dejing Dou

SUK 1.0: A New Training Corpus for Linguistic Annotation of Modern Standard Slovene (2024.lrec-main)

Challenge:	Existing models rely on a single segmentation token whose hidden state implicitly encodes both semantic reasoning and spatial localization . Existing methods rely only on SEG>, which encodes semantic reasoning, limiting the model's ability to explicitly disentangle what to segment from where to segment.
Approach:	They propose a method which reformulates reasoning segmentation as a structured conditional generation process over image tokens conditioned on language grounded query banks.
Outcome:	The proposed model bridges token-level predictions and pixel-level supervision by decoupling spatial grounding from semantic reasoning through structured language grounded query banks.

Copied to clipboard

Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Tomaž Erjavec, Polona Gantar, Simon Krek, Tina Munda, Nejc Robida, Luka Terčon, Slavko Zitnik

Challenge:	a training corpus for linguistic annotation of modern standard Slovene has been in continuous development for 15 years.
Approach:	They introduce an upgrade of a training corpus for linguistic annotation of modern standard Slovene.
Outcome:	The revised corpus, built on its predecessor, doubles in size and depth of annotation layers.

Massively Multilingual Joint Segmentation and Glossing (2026.acl-long)

Copied to clipboard

Michael Ginn, Lindia Tjuatja, Enora Rice, Ali Marashian, Maria Valentini, Jasmine Xu, Graham Neubig, Alexis Palmer

BoundRL: Efficient Token-level Structured Text Segmentation through Reinforced Boundary Generation (2026.findings-acl)

Challenge:	Existing models generate morpheme-level glosses but assign them to whole words without predicting the actual morphological boundaries, making them less interpretable and therefore untrustworthy to human annotators.
Approach:	They propose to use neural networks to predict interlinear glosses and morphological segmentation from raw text.
Outcome:	The proposed model outperforms GlossLM on glossing and beats open-source models on segmentation, glossing, and alignment.

Copied to clipboard

Haoyuan Li, Zhengyuan Shen, Sullam Jeoung, Yueyan Chen, Jiayu Li, Qi Zhu, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala