CRF

Few-Shot Event Detection with Prototypical Amortized Conditional Random Field (2021.findings-acl)

Challenge:	Existing work on pharmacological entities requires manual annotation of these units.
Approach:	They propose an approach to task 1 of the PharmaCoNER Challenge to recognize pharmacological entities on a spanish corpus.
Outcome:	The proposed approach achieves 89.76% score on a spanish corpus based on pre-trained embeddings and 90.52% score on domain-specific embeddables.

Copied to clipboard

Xin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu, Wang Yubin, Bin Wang

IxaMed at PharmacoNER Challenge 2019 (D19-57)

Challenge:	Existing approaches to event detection ignore the trigger discrepancy and cause errors.
Approach:	They propose a unified model which converts a few-shot tagging problem into a single-shot model by using a Gaussian distribution.
Outcome:	The proposed model performs better than existing identifythen-classify models on a few-shot tagging problem with a double-part taging scheme.

Copied to clipboard

Xabier Lahuerta, Iakes Goenaga, Koldo Gojenola, Aitziber Atutxa Salazar, Maite Oronoz

Graph Convolution for Multimodal Information Extraction from Visually Rich Documents (N19-2)

Challenge:	The aim of this paper is to present our approach in the PharmacoNER 2019 task.
Approach:	They propose to use a Bi-LSTM with a CRF to identify named entities from clinical case studies written in Spanish.
Outcome:	The proposed approach achieves the best score (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records with contextual string embedds.

Copied to clipboard

Xiaojing Liu, Feiyu Gao, Qiong Zhang, Huasha Zhao

Opinion Mining with Deep Contextualized Embeddings (N19-3)

Challenge:	Visually rich documents (VRDs) present information in the form of both text and vision.
Approach:	They propose a graph convolution based model to combine textual and visual information presented in VRDs.
Outcome:	The proposed model outperforms existing models on two real-world datasets.

Copied to clipboard

Wen-Bin Han, Noriko Kando

Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking (D19-55)

Challenge:	Existing methods for opinion expression detection are based on token-level sequence labeling .
Approach:	They propose to use BERT and conditional random field embedders to detect opinion expressions.
Outcome:	The proposed model outperforms ELMo embedders in opinion expression detection.

Copied to clipboard

Nathanael Chambers, Timothy Forman, Catherine Griswold, Kevin Lu, Yogaish Khastgir, Stephen Steckler

Robustness in NLP

Challenge:	Illicit activity on the Web often obscures information between client and seller, such as the seller’s phone number.
Approach:	They propose to use a dataset to model adversarial noise in a text extraction system and propose a visual character language model to interpret unseen unicode characters.
Outcome:	The proposed model improves number recognition by 89% over a CRF with a CNN and shows that unicode characters can be translated to unicoding.

Deep neural model with enhanced embeddings for pharmaceutical and chemical entities recognition in Spanish clinical text (D19-57)

Copied to clipboard

Renzo Rivera, Paloma Martínez

Towards a Standardized Dataset on Indonesian Named Entity Recognition (2020.aacl-srw)

Challenge:	Currently, the number of biomedical literature is growing at an exponential rate.
Approach:	They propose a Deep Learning architecture for pharmaceutical and chemical Named Entity Recognition in Spanish clinical cases texts.
Outcome:	The proposed model outperforms the state-of-the-art methods on the PharmaCoNER corpus . the proposed model is based on two bidirectional long-term memory and conditional random field networks .

Copied to clipboard

Siti Oryza Khairunnisa, Aizhan Imankulova, Mamoru Komachi

Sentence Suggestion of Japanese Functional Expressions for Chinese-speaking Learners (P18-4)

Challenge:	Named entity recognition (NER) tasks in the Indonesian language are still lacking data for the majority of languages, including Indonesian.
Approach:	They re-annotated an open dataset with 2,000 sentences and compared the results with a bidirectional long short-term memory and conditional random field approach.
Outcome:	The proposed approach improved the prediction score and consistent organization tag for the Indonesian language.

Copied to clipboard

Jun Liu, Hiroyuki Shindo, Yuji Matsumoto

Text Clustering

Challenge:	a large number of Chinese characters are commonly used both in Chinese and Japanese.
Approach:	They propose a computer-assisted learning system for Chinese-speaking learners of Japanese as a second language (JSL) they use a free Japanese morphological analyzer MeCab to learn Japanese functional expressions with suggestion of appropriate example sentences.
Outcome:	The proposed system automatically recognizes Japanese functional expressions using a free Japanese morphological analyzer and is retrained on a new conditional random field model.

Neural Architectures for Fine-Grained Propaganda Detection in News (D19-50)

Copied to clipboard

Pankaj Gupta, Khushbu Saxena, Usama Yaseen, Thomas Runkler, Hinrich Schütze

NCRF++: An Open-source Neural Sequence Labeling Toolkit (P18-4)

Challenge:	MIC-CIS is a fine grained propaganda detection system . previous work focused on document level, labeling articles as propaganda .
Approach:	They propose to use different neural architectures to jointly perform propaganda detection tasks . they also investigate different ensemble schemes such as majority-voting, relax-vote, etc.
Outcome:	The proposed system performs sentences and fragment level propaganda detection tasks.

Copied to clipboard

Jie Yang, Yue Zhang

Challenge:	Existing statistical approaches to neural sequence labeling have been used for many tasks.
Approach:	They describe a toolkit for neural sequence labeling that provides a CRF inference layer for quick implementation.
Outcome:	The toolkit is based on PyTorch and can be run on GPUs.

Multi-Dialect Arabic POS Tagging: A CRF Approach (L18-1)

Copied to clipboard

Kareem Darwish, Hamdy Mubarak, Ahmed Abdelali, Mohamed Eldesouki, Younes Samih, Randah Alharbi, Mohammed Attia, Walid Magdy, Laura Kallmeyer

Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text (D19-62)

Challenge:	Existing work on dialectal POS tagging is rather scant with POS tags for most dialects being nonexistent or of limited availability.
Approach:	They propose a dataset of POS-tagged Arabic tweets in four major dialects and a tagging guideline for each dialect.
Outcome:	The proposed model can tag four different dialects with an average accuracy of 89.3%.

Copied to clipboard

Hanna Berg, Taridzo Chomutare, Hercules Dalianis

Challenge:	Several ethical and scientific issues arise regarding the balance between maintaining patient confidentiality and the need for wider application of trained models.
Approach:	They propose to use pseudonymised clinical text as training data to de-identify real clinical text in other hospitals.
Outcome:	The proposed model performed better for some PHI information than the standard model and poor performance on Location and Health Care Unit information.

Filtered Semi-Markov CRF (2023.findings-emnlp)

Copied to clipboard

Urchade Zaratiana, Nadi Tomeh, Niama El Khbir, Pierre Holat, Thierry Charnois

A k-Nearest Neighbor Approach towards Multi-level Sequence Labeling (N19-2)

Challenge:	Existing methods for sequence labeling tasks such as Named Entity Recognition (NER) suffer from quadratic complexity over sequence length and poor performance compared to CRF.
Approach:	They propose a variant of Semi-Markov CRF that incorporates a filtering step to eliminate irrelevant segments, reducing complexity and search space.
Outcome:	The proposed method outperforms both CRF and Semi-CRF on several NER benchmarks while being significantly faster.

Copied to clipboard

Yue Chen, John Chen

Bag of Experts Architectures for Model Reuse in Conversational Language Understanding (N18-3)

Challenge:	Existing methods for complex dialog management require limited training data.
Approach:	They propose a method for intent recognition for complex dialog management in low resource situations . they use windowed word n-grams, POS tag n grams and pre-trained word embeddings as features .
Outcome:	The proposed method performs better with less than 1% of the data size than existing methods but requires considerably more data.

Copied to clipboard

Rahul Jha, Alex Marin, Suvamsh Shivaprasad, Imed Zitouni

A Named Entity Recognition Shootout for German (P18-2)

Challenge:	Slot tagging is a key component of natural language understanding systems for personal digital assistants.
Approach:	They propose to use a bag of experts architecture to reuse domain data for slot tagging models.
Outcome:	Experiments with 10 domains show that the proposed models outperform baseline models by 5.06% and 12.16% when training with only 25% of the training data.

Copied to clipboard

Martin Riedl, Sebastian Padó

Linguistically Informed Relation Extraction and Neural Architectures for Nested Named Entity Recognition in BioNLP-OST 2019 (D19-57)

Challenge:	Named entity recognition and classification (NER) is a central component in many natural language processing pipelines.
Approach:	They propose to build a model for German named entity recognition that performs at the state of the art for both contemporary and historical texts.
Outcome:	The proposed model outperforms the CRF and BiLSTM on large and small datasets.

Copied to clipboard

Pankaj Gupta, Usama Yaseen, Hinrich Schütze

TeluguNER: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers (2022.acl-srw)

Challenge:	Named Entity Recognition (NER) and Relation Extraction (RE) are essential tools in distilling knowledge from biomedical literature.
Approach:	They propose to use Named Entities to perform nested entities extraction, Entity Normalization and Relation Extraction to generalize the approach to different languages.
Outcome:	The proposed approach can be generalized to different languages and showed it’s effectiveness for English and Spanish text.

Copied to clipboard

Suma Reddy Duggenpudi, Subba Reddy Oota, Mounika Marreddy, Radhika Mamidi

Reevaluating Argument Component Extraction in Low Resource Settings (D19-61)

Challenge:	Named Entity Recognition (NER) is a successful and well-researched problem in English due to the availability of resources.
Approach:	They propose to use two annotated NER datasets for the Telugu language . they compare the finetuned Telugus model with the existing model in NER .
Outcome:	The proposed models outperform existing models on a large dataset of 38,363 sentences on telugu and other languages.

Copied to clipboard

Anirudh Joshi, Timothy Baldwin, Richard Sinnott, Cecile Paris

Multiple Character Embeddings for Chinese Word Segmentation (P19-2)

Challenge:	Argument component extraction is a challenging and complex high-level semantic extraction task.
Approach:	They propose to use character-level, GloVe, ELMo, and BERT encodings to compare arguments extracted using standard BiLSTM-CRF encoders.
Outcome:	The proposed approaches perform better than baselines in higher-level semantic extraction tasks and suggest future improvements.

Copied to clipboard

Jianing Zhou, Jingkang Wang, Gongshen Liu

Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation (D19-52)

Challenge:	Chinese word segmentation is regarded as character-based sequence labeling task in most current work but it neglects important fact: Chinese characters contain both semantic and phonetic meanings.
Approach:	They propose a shared bi-LSTM-CRF model which fuses linguistic features efficiently by sharing the LSTM network during the training procedure.
Outcome:	The proposed model achieves state-of-the-art in AS and CityU corpora without external lexical resources.

Copied to clipboard

Ali Fadel, Ibraheem Tuffaha, Bara’ Al-Jawarneh, Mahmoud Al-Ayyoub

Machine Translation

Challenge:	a number of Arabic text diacritizers use diacritics to convey information about meaning of a word . Arabic text to speech (TTS) requires a complex process to determine the correct diacritical for each character .
Approach:	They propose to use Arabic diacritization to enhance machine translation models . they propose to build automatic Arabic text diacritics using two approaches .
Outcome:	The proposed models are either better or on par with other models, which require language-dependent post-processing steps, unlike ours.

Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition (2021.tacl-1)

Copied to clipboard

Abbas Ghaddar, Philippe Langlais, Ahmad Rashid, Mehdi Rezagholizadeh

Named Entity Recognition

Challenge:	Name Regularity Bias is a problem in NER models that use contextual information to predict the type of an ambiguous entity.
Approach:	They propose a model-agnostic training method that adds learnable adversarial noise to some entity mentions to improve their accuracy.
Outcome:	The proposed method outperforms feature-based models on name regularity bias . it adds learnable adversarial noise to some entity mentions, leading to gains .

Building a Corpus from Handwritten Picture Postcards: Transcription, Annotation and Part-of-Speech Tagging (L18-1)

Copied to clipboard

Kyoko Sugisaki, Nicolas Wiedmer, Heiko Hausendorf

Hybrid semi-Markov CRF for Neural Sequence Labeling (P18-2)

Challenge:	In this paper, we describe the processes and challenges of digitalisation, manual transcription, and manual annotation of over 11,000 postcards.
Approach:	They describe the processes and challenges of digitalisation, manual transcription, and manual annotation of over 11,000 postcards written in German and Swiss German.
Outcome:	The proposed system outperforms state-of-the-art taggers in the evaluation of the 'picture postcard corpus' containing over 11,000 handwritten postcards .

Copied to clipboard

Zhixiu Ye, Zhen-Hua Ling

Speaker-change Aware CRF for Dialogue Act Classification (2020.coling-main)

Challenge:	Existing conditional random fields (CRFs) use hand-crafted features to perform sequence labeling tasks.
Approach:	They propose to use semi-Markov conditional random fields for neural sequence labeling in natural language processing to extract features from segments instead of words.
Outcome:	The proposed model achieves state-of-the-art when no external knowledge is used.

Copied to clipboard

Guokan Shang, Antoine Tixier, Michalis Vazirgiannis, Jean-Pierre Lorré

Improve Neural Entity Recognition via Multi-Task Data Selection and Constrained Decoding (N18-2)

Challenge:	Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer.
Approach:	They propose to modify the CRF layer to take speaker-change into account and learn meaningful transition patterns conditioned on speaker-changing DA labels.
Outcome:	The proposed model outperforms the original model with wide margins for some DA labels.

Copied to clipboard

Huasha Zhao, Yi Yang, Qiong Zhang, Luo Si

Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role Labeling (2023.findings-acl)

Challenge:	Entity recognition is a widely benchmarked task in natural language processing . a neural architecture called BiLSTM-CRF is used to model the language sequences .
Approach:	They propose a neural architecture called BiLSTM-CRF to model the language sequences.
Outcome:	The proposed system achieves state-of-the-art on English entity recognition task and also in other languages.

Copied to clipboard

Wei Liu, Songlin Yang, Kewei Tu

Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data? (C18-1)

Challenge:	Span-based semantic role labeling is traditionally tackled by BIObased sequence labeling approaches.
Approach:	They propose to decompose the edge from predicate word to argument span into three different edges, enabling higher-order inference.
Outcome:	The proposed model outperforms vanilla MFVI on span-based semantic role labeling benchmarks.

Copied to clipboard

Yi Zhang, Xu Sun, Shuming Ma, Yang Yang, Xuancheng Ren

LegalSeg: Unlocking the Structure of Indian Legal Judgments Through Rhetorical Role Classification (2025.findings-naacl)

Challenge:	Existing neural models take long distance dependencies into account when predicting the tag of the current token.
Approach:	They propose a method to capture long distance tag dependencies and use them for dependency analysis.
Outcome:	The proposed model can predict multiple tags for the current token without taking dependencies between tags into account.

Copied to clipboard

Shubham Kumar Nigam, Tanmay Dubey, Govind Sharma, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya

Text Classification

Challenge:	a lack of large-scale annotated datasets hinders effective training of ML models . despite advances in semantic segmentation, challenges persist in distinguishing between closely related roles .
Approach:	They propose a large annotated dataset for semantic segmentation of legal documents . they use a rhetorical role classification model to compare performance against other models .
Outcome:	The largest annotated dataset for this task outperforms models relying on sentence-level features.

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

Copied to clipboard

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

Constituency Lattice Encoding for Aspect Term Extraction (2020.coling-main)

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

Yunyi Yang, Kun Li, Xiaojun Quan, Weizhou Shen, Qinliang Su

Sentiment Analysis

Challenge:	a challenge for aspect term extraction is to extract phrase-level aspect terms . a constituency lattice structure is constructed using the span annotations of constituents of a sentence .
Approach:	They propose to incorporate the span annotations of constituents of a sentence to leverage syntactic information in neural network models.
Outcome:	The proposed model outperforms existing models on two benchmark datasets.

Augmenting Small Data to Classify Contextualized Dialogue Acts for Exploratory Visualization (2020.lrec-1)

Copied to clipboard

Abhinav Kumar, Barbara Di Eugenio, Jillian Aurisano, Andrew Johnson

Learning with Structured Representations for Negation Scope Extraction (P18-2)

Challenge:	a new corpus of conversations is being developed to support data visualization exploration . we use data augmentation to improve our methods for dialogue act classification .
Approach:	They propose to use a corpus of conversations to annotate contextualized dialogue acts . they highlight how thinking aloud affects interpretation of dialogue acts in the context .
Outcome:	The proposed AI can support visualization exploration with a small corpus of conversations . the proposed AI outperforms existing models in terms of performance and performance .

Copied to clipboard

Hao Li, Wei Lu

Frustratingly Simple Few-Shot Slot Tagging (2021.findings-acl)

Challenge:	Existing approaches to negation scope detection have been criticized for capturing information related to negations, long-distance dependencies and structural information.
Approach:	They propose to use conditional random fields, semi-Markov CRF and latent-variable CRF models to capture useful information such as long-distance dependencies and some latent structural information.
Outcome:	The proposed approaches can capture useful information such as features related to negation cue, long-distance dependencies and some latent structural information.

Copied to clipboard

Jianqiang Ma, Zeyu Yan, Chang Li, Yang Zhang

K-LegalDeID: A Benchmark Dataset and KLUEBERT-CRF for De-identification in Korean Court Judgments (2026.eacl-long)

Challenge:	Existing fewshot methods for slot tagging are weak in encoding slot name semantics and slot dependencies.
Approach:	They propose a simple and effective few-shot model for slot tagging which incorporates machine reading comprehension (MRC) using source domain and target domain data.
Outcome:	The proposed model outperforms state-of-the-art methods on the SNIPS dataset.

Copied to clipboard

Wooseok Choi, Hyungbin Kim, Yon Dohn Chung

Unsupervised Recurrent Neural Network Grammars (N19-1)

Challenge:	Korean legal system mandates public access to court judgments to ensure judicial transparency, but this requirement conflicts with privacy protection obligations due to the prevalence of Personally Identifiable Information (PII) in legal documents.
Approach:	They propose a large-scale benchmark dataset and an efficient KLUEBERT-CRF model for de-identification for Korean court judgments.
Outcome:	The proposed model achieves state-of-the-art performance with an entity-level micro F1 score of 0.9923.

Copied to clipboard

Yoon Kim, Alexander Rush, Lei Yu, Adhiguna Kuncoro, Chris Dyer, Gábor Melis

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

Challenge:	RNNGs model syntax and structure by incrementally generating a syntax tree and sentence in a top-down, left-to-right order.
Approach:	They explore unsupervised learning of recurrent neural network grammars for language modeling and grammar induction.
Outcome:	The proposed model outperforms standard sequential language models and improves parsing performance.

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.

Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media (N18-1)

Copied to clipboard

Gustavo Aguilar, Adrian Pastor López-Monroy, Fabio González, Thamar Solorio

Development of a Benchmark Corpus to Support Entity Recognition in Job Descriptions (2022.lrec-1)

Challenge:	Current approaches to Named Entity Recognition (NER) are effective in formal text, but they fail on informal text, where improper grammatical structures, spelling inconsistencies, and slang vocabulary prevail.
Approach:	They propose a multitask end-to-end bidirectional long short-term memory (BLSTM)-Conditional Random Field (CRF) network with two CRF classifiers and a feature extractor that transfers learning to a CRF for prediction.
Outcome:	The proposed models outperform the current state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments.

Copied to clipboard

Thomas Green, Diana Maynard, Chenghua Lin

Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (2020.acl-main)

Challenge:	Existing tools for identifying and extracting salient entities from job descriptions are limited by the lack of publicly available training data.
Approach:	They propose to use a standard definition of entities and a training corpus to develop a benchmark Entity Recognition (ER) model.
Outcome:	The proposed model achieves an F1 score of 0.59 from 18.6k entities comprising five types (Skill, Qualification, Experience, Occupation, and Domain).

Copied to clipboard

Yutai Hou, Wanxiang Che, Yongkui Lai, Zhihan Zhou, Yijia Liu, Han Liu, Ting Liu

Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation (N19-1)

Challenge:	Existing few-shot learning methods for slot tagging are based on similarity-based methods, but they are difficult to apply to an unseen domain due to the discrepancy of label sets.
Approach:	They propose a label-enhanced task-adaptive projection network to transfer abstract label dependency patterns as transition scores into the conditional random field (CRF) Experimental results show that their model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.
Outcome:	The proposed model outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.

Copied to clipboard

Tasnim Mohiuddin, Thanh-Tung Nguyen, Shafiq Joty

Speech & Audio in NLP

Challenge:	asynchronous domains lack large labeled datasets to train an effective speech act recognition model.
Approach:	They propose methods to leverage abundant unlabeled conversational data and available labeled data from synchronous domains to train an effective SAR model.
Outcome:	The proposed method outperforms existing methods when trained on in-domain data only.

Investigating Non-local Features for Neural Constituency Parsing (2022.acl-long)

Copied to clipboard

Leyang Cui, Sen Yang, Yue Zhang

Challenge:	Constituency parsers have been able to achieve competitive performance by using local features.
Approach:	They propose to inject non-local features into the training process of a local span-based parser by predicting constituent n-gram non-local patterns and ensuring consistency between constituents and local constituents.
Outcome:	The proposed method outperforms the self-attentive parser in multi-lingual and zero-shot cross-domain settings.

Sentence-Level Resampling for Named Entity Recognition (2022.naacl-main)

Copied to clipboard

Xiaochen Wang, Yue Wang

Masked Conditional Random Fields for Sequence Labeling (2021.naacl-main)

Challenge:	named entity recognition (NER) tasks are often dominated by the majority of non-entity tokens in text . a data imbalance problem is causing the NER models to ignore named entities .
Approach:	They propose a set of sentence-level resampling methods to reduce data imbalance . they use a training sentence to compute the importance of each training sentence based on its tokens and entities .
Outcome:	The proposed methods outperform sub-sentence-level resampling, data augmentation, and loss functions on multiple corpora.

Copied to clipboard

Tianwen Wei, Jianwei Qi, Shenghuan He, Songtao Sun

Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers (2020.findings-emnlp)

Challenge:	Conditional Random Fields (CRF) based neural models are among the most performant for sequence labeling problems, but they can sometimes generate illegal sequences of tags.
Approach:	They propose a conditional random field-based model that imposes restrictions on candidate paths during both training and decoding phases.
Outcome:	The proposed method improves on existing CRF models with near zero additional cost.

Copied to clipboard

Brian Lester, Daniel Pressel, Amy Hemmeter, Sagnik Ray Choudhury, Srinivas Bangalore

Uncertainty-Aware Label Refinement for Sequence Labeling (2020.emnlp-main)

Challenge:	Named entity recognition models use a conditional random field as the final layer . current work eschews prior knowledge of how the span encoding scheme works .
Approach:	They propose to constrain the output to suppress illegal transitions to train a tagger with a cross-entropy loss twice as fast as a CRF.
Outcome:	The proposed model trains twice as fast as a CRF with statistically insignificant differences in F1 . the proposed model is open source and can be used in PyTorch and TensorFlow.

Copied to clipboard

Tao Gui, Jiacheng Ye, Qi Zhang, Zhengyan Li, Zichu Fei, Yeyun Gong, Xuanjing Huang

Green & Sustainable NLP

Challenge:	Conditional random fields (CRF) for label decoding have been a problem for many tasks.
Approach:	They propose a two-stage label decoding framework that model long-term label dependencies while being much more computationally efficient.
Outcome:	The proposed method outperforms the CRF-based methods and greatly accelerates the inference process.

Simple Yet Powerful: An Overlooked Architecture for Nested Named Entity Recognition (2022.coling-1)

Copied to clipboard

Matias Rojas, Felipe Bravo-Marquez, Jocelyn Dunstan

Unsupervised Cross-Lingual Adaptation of Dependency Parsers Using CRF Autoencoders (2020.findings-emnlp)

Challenge:	Named Entity Recognition (NER) is an important task in Natural Language Processing that aims to identify text spans belonging to predefined categories.
Approach:	They propose to revisit the Multiple LSTM-CRF (MLC) model, a simple, overlooked, yet powerful approach based on training independent sequence labeling models for each entity type.
Outcome:	The proposed model achieves state-of-the-art results in the Chilean Waiting List corpus by including pre-trained language models.

Copied to clipboard

Zhao Li, Kewei Tu

A LSTM Approach with Sub-Word Embeddings for Mongolian Phrase Break Prediction (C18-1)

Challenge:	Existing work on cross-lingual adaptation of dependency parsers without annotated target corpora focuses on discriminative source parser ignoring unannotated corporata .
Approach:	They propose to use unsupervised discriminative parsers to adapt dependency parser to unannotated target corpora without a supervised generative parsing method.
Outcome:	The proposed method significantly outperforms previous methods.

Copied to clipboard

Rui Liu, Feilong Bao, Guanglai Gao, Hui Zhang, Yonghe Wang

AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction (2023.eacl-main)

Challenge:	Existing word embedding methods for Mongolian PB prediction are expensive and time-consuming.
Approach:	They propose to use Mongolian word embedding to build a robust Mongolian PB prediction model . they encode sub-word units and feed it to LSTM to decode the best corresponding PB label .
Outcome:	The proposed model outperforms traditional model using manual features and achieves 7.49% gain.

Copied to clipboard

Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, Xiang Ren

Negative Focus Detection via Contextual Attention Mechanism (D19-1)

Challenge:	Named entity recognition models have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations.
Approach:	They propose a framework that automatically generates and leverages “entity triggers” which are human-readable cues in the text that help guide the model to make better decisions.
Outcome:	The proposed framework outperforms the RoBERTa-CRF baseline by nearly 0.5 F1 points on three well-studied datasets.

Copied to clipboard

Longxiang Shen, Bowei Zou, Yu Hong, Guodong Zhou, Qiaoming Zhu, AiTi Aw

Challenge:	Negation is a universal but complicated linguistic phenomenon that reverses the polarity of a statement or its property into opposite.
Approach:	They propose a framework which consists of a Bidirectional Long Short-Term Memory neural network and a Conditional Random Fields layer to capture contextual information.
Outcome:	The proposed framework improves on the SEM’12 shared task corpus, yielding an absolute improvement of 2.11% over the state-of-the-art.

Learning Named Entity Tagger using Domain-Specific Dictionary (D18-1)

Copied to clipboard

Jingbo Shang, Liyuan Liu, Xiaotao Gu, Xiang Ren, Teng Ren, Jiawei Han

An Investigation of Potential Function Designs for Neural CRF (2020.findings-emnlp)

Challenge:	Existing methods to build reliable named entity recognition systems require large amounts of manually-labeled training data.
Approach:	They propose a revised fuzzy CRF layer to handle tokens with multiple possible labels to address noisy distant supervision.
Outcome:	The proposed model can handle tokens with multiple possible labels under the traditional framework and improves on the existing model with a new Tie or Break scheme.

Copied to clipboard

Zechuan Hu, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Improving Multi-label Malevolence Detection in Dialogues through Multi-faceted Label Correlation Enhancement (2022.acl-long)

Challenge:	Existing approaches to sequence labeling are based on the neural linear-chain CRF model.
Approach:	They propose a series of increasingly expressive potential functions for neural CRF models that integrate emission and transition functions and explicitly take contextual words as input.
Outcome:	The proposed model consistently achieves the best performance on the decomposed quadrilinear potential function based on the representations of two neighboring labels and two neighbored words.

Copied to clipboard

Yangjun Zhang, Pengjie Ren, Wentao Deng, Zhumin Chen, Maarten Rijke

Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging (2022.findings-acl)

Challenge:	Current methods for detecting dialogue malevolence neglect label correlation.
Approach:	They propose to crowdsource a multi-label dataset for detecting malevolent dialogue responses and a model with label correlation enhanced CRF to measure the correlation between malevolence and negative emotions.
Outcome:	The proposed model outperforms the best performing baseline method on precision, recall, F1, and Jaccard score by 16.1%, 11.9%, 12.0%, and 6.1% on malevolence.

Copied to clipboard

Houquan Zhou, Yang Li, Zhenghua Li, Min Zhang

Understanding the Cooking Process with English Recipe Text (2023.findings-acl)

Challenge:	Large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks, but they fail to achieve state-of-the-art (SOTA) performance.
Approach:	They propose a Guassian HMM variant for unsupervised POS tagging that incorporates contexualized word representations into the decoder.
Outcome:	The proposed model outperforms state-of-the-art models on Penn Treebank and multilingual Universal Dependencies treebank v2.0.

Copied to clipboard

Yi Fan, Anthony Hunter

Machine Translation

Challenge:	Existing approaches to translate recipes into a flow graph have performance problems . authors propose a framework to construct a graph from recipe text .
Approach:	They propose a framework that can be used to translate recipes into a flow graph representation.
Outcome:	The proposed framework can predict the edge label and achieve the overall F1 score of 92.2 on the English recipe flow graph corpus.

Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling (2022.acl-long)

Copied to clipboard

Elena Álvarez-Mellado, Constantine Lignos

Noisy-Labeled NER with Confidence Estimation (2021.naacl-main)

Challenge:	a corpus of Spanish newswire rich in unassimilated lexical borrowings is used to identify the language of a word.
Approach:	They propose to annotate a corpus of Spanish newswire rich in unassimilated lexical borrowings and evaluate how models perform on this task.
Outcome:	The proposed model outperforms models fed with subword embeddings and Transformer-based embeddables on the Spanish newswire corpus.

Copied to clipboard

Kun Liu, Yao Fu, Chuanqi Tan, Mosha Chen, Ningyu Zhang, Songfang Huang, Sheng Gao

Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments (2020.coling-main)

Challenge:	Recent studies in deep learning have shown significant progress in named entity recognition (NER) . however, most existing works assume clean data annotation, while real-world data typically involve a large amount of noises.
Approach:	They propose a confidence estimation approach for named entity recognition using noisy labels using local and global independence assumptions.
Outcome:	The proposed method marginalizes out labels of low confidence with a CRF model and integrates it into a self-training framework for boosting performance.

Copied to clipboard

Feng Nie, Jinpeng Wang, Chin-Yew Lin

Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets (D18-1)

Challenge:	Existing methods for data-to-text generation use a large-scale training corpus to learn semantic correspondences between structured input data and associated texts.
Approach:	They propose a local-to-global alignment framework that uses local and global models to learn semantic correspondences from large-scale datasets.
Outcome:	The proposed framework can be generalized to restaurant and computer domains and improve alignment accuracy.

Copied to clipboard

Nathan Greenberg, Trapit Bansal, Patrick Verga, Andrew McCallum

Evaluating the Utility of Hand-crafted Features in Sequence Labelling (D18-1)

Challenge:	Existing large labeled text datasets contain labels for multiple subsets of biomedical entity types, but it is rare to find large labeling datasets containing all desired entity types together.
Approach:	They propose a method for training a single CRF extractor from multiple datasets with disjoint or partially overlapping sets of entity types.
Outcome:	The proposed method improves NER F1 over training in isolation on biocreative V CDR, biocreativ VI ChemProt and MedMentions datasets.

Copied to clipboard

Minghao Wu, Fei Liu, Trevor Cohn

Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Features (2021.eacl-main)

Challenge:	Conventional wisdom is that hand-crafted features are redundant for deep learning models . authors propose a method for using handcrafted features in a hybrid learning approach .
Approach:	They propose a method for exploiting handcrafted features as part of a hybrid learning approach.
Outcome:	The proposed method outperforms baseline models on a named entity recognition task and reduces training requirements to 60% while maintaining the same predictive accuracy.

Copied to clipboard

Thomas Haider

Evaluating Pretrained Transformer-based Models on the Task of Fine-Grained Named Entity Recognition (2020.coling-main)

Challenge:	a prerequisite for the computational study of literature is the availability of properly digitized texts with reliable meta-data and ground-truth annotation.
Approach:	They propose to annotate prosodic features in large poetry corpora for English and German and train corpus driven neural models that enable large scale analysis.
Outcome:	The proposed models outperform baseline and BERT-based approaches in English and german and show that they learn foot boundaries better when jointly predicting syllable stress, aesthetic emotions and verse measures benefit from each other.

Copied to clipboard

Cedric Lothritz, Kevin Allix, Lisa Veiber, Tegawendé F. Bissyandé, Jacques Klein

Autoregressive Text Generation Beyond Feedback Loops (D19-1)

Challenge:	Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP).
Approach:	They compare three transformer-based names to two non-transformer-based ones . they find transformer-derived models incrementally outperform non-tranformer models .
Outcome:	The proposed models outperform the studied models in most domains with respect to the F1 score.

Copied to clipboard

Florian Schmidt, Stephan Mandt, Thomas Hofmann

GeCoTagger: Annotation of German Verb Complements with Conditional Random Fields (L18-1)

Challenge:	Autoregressive feedback exposes the evolution of the hidden state trajectory to potential biases from well-known train-test discrepancies.
Approach:	They combine a latent state space model with a CRF observation model to investigate the state evolution of a hidden state trajectory.
Outcome:	The proposed model performs better on unconditional sentence generation compared to baselines while avoiding some prototypical failure modes.

Copied to clipboard

Roman Schneider, Monica Fürbacher

Tagging

Challenge:	Complement phrases are essential for constructing well-formed sentences in German.
Approach:	They propose an algorithm which can identify and classify complement phrases of any German verb in any written sentence context.
Outcome:	The proposed algorithm can identify and classify complement phrases of any German verb in any written sentence context.

Zero-shot Script Parsing (2022.coling-1)

Copied to clipboard

Fangzhou Zhai, Vera Demberg, Alexander Koller

SiNER: A Large Dataset for Sindhi Named Entity Recognition (2020.lrec-1)

Challenge:	Existing resources cover only a small number of tasks, limiting its practical usefulness.
Approach:	They propose a zero-shot learning approach to script parsing which enables us to acquire script knowledge without domain-specific annotations.
Outcome:	The proposed model outperforms a previous model with scenario-specific supervision and achieves 68.1/74.4 average F1 for event / participant parsing.

Copied to clipboard

Wazir Ali, Junyu Lu, Zenglin Xu

Pretrained Language Models for Sequential Sentence Classification (D19-1)

Challenge:	Named entity recognition is an essential lower-level task in natural language processing (NLP).
Approach:	They propose to develop a named entity recognition dataset for low-resourced Sindhi language with quality baselines.
Outcome:	The proposed dataset is likely to be a significant resource for statistical Sindhi language processing.

Copied to clipboard

Arman Cohan, Iz Beltagy, Daniel King, Bhavana Dalvi, Dan Weld

Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction (2021.acl-long)

Challenge:	Recent successful models for document-level understanding have used hierarchical encoding and CRFs to capture dependencies between subsequent labels.
Approach:	They propose a pretrained language model that captures contextual dependencies without hierarchical encoding nor a CRF.
Outcome:	The proposed model captures contextual dependencies without hierarchical encoding nor a CRF on four datasets, including a new dataset of structured scientific abstracts.

Copied to clipboard

Piji Li, Shuming Shi

Towards Multilingual Interlinear Morphological Glossing (2023.findings-emnlp)

Challenge:	Experimental results demonstrate the effectiveness of Tail-to-Tail (TtT) non-autoregressive sequence prediction for Chinese Grammatical Error Correction (CGEC)
Approach:	They propose a framework for Chinese Grammatical Error Correction (CGEC) that uses a BERT-initialized Transformer Encoder to model the error positions.
Outcome:	The proposed framework solves the problem of Chinese Grammatical Error Correction (CGEC) by modeling the token dependencies.

Copied to clipboard

Shu Okabe, François Yvon

Multilinguality

Challenge:	Interlinear Morphological Glosses are annotations produced in the context of language documentation.
Approach:	They propose to use a conditional random field to label morphs in L1 and then align them to L2 words to facilitate the process.
Outcome:	The proposed method outperforms baselines in several under-resourced languages and is effective and data-efficient.

Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models (2022.findings-emnlp)

Copied to clipboard

Siddhant Arora, Siddharth Dalmia, Brian Yan, Florian Metze, Alan W Black, Shinji Watanabe

Dependency-Guided LSTM-CRF for Named Entity Recognition (D19-1)

Challenge:	End-to-end spoken language understanding systems model sequence labeling as a sequence prediction task causing a divergence from its well-established token-level tagging formulation.
Approach:	They propose to model sequence labeling as a sequence prediction task . their systems explicitly separate the added complexity of recognizing spoken mentions from the NLU task of sequence labelling .
Outcome:	The proposed systems outperform both cascaded and direct models on a labeling task of named entity recognition across SLU benchmarks.

Copied to clipboard

Zhanming Jie, Wei Lu

Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting (2024.findings-emnlp)

Challenge:	Named entity recognition (NER) is one of the most important and fundamental tasks in natural language processing (NLP).
Approach:	They propose a dependency-guided model to encode dependency trees and capture their properties for named entity recognition.
Outcome:	The proposed model improves named entity recognition performance on standard datasets.

Copied to clipboard

Marco Naguib, Xavier Tannier, Aurélie Névéol

Hierarchically-Refined Label Attention Network for Sequence Labeling (D19-1)

Challenge:	Named Entity Recognition (NER) is a critical task in information extraction that is not covered in recent benchmarks.
Approach:	They compare 13 auto-regressive models using prompting and 16 masked models using fine-tuning on 14 NER datasets covering English, French and Spanish.
Outcome:	The proposed models outperform auto-regressive models in English, French and Spanish on 14 NER datasets.

Copied to clipboard

Leyang Cui, Yue Zhang

Named Entity Recognition via Noise Aware Training Mechanism with Data Filter (2021.findings-acl)

Challenge:	Conditional random fields (CRF) is a powerful model for statistical sequence labeling, but it does not give much information gain over strong neural encoding.
Approach:	They propose a hierarchically-refined label attention network which captures potential long-term label dependency by giving each word incrementally refined label distributions with hierarchical attention.
Outcome:	The proposed model improves POS tagging accuracy and speeds up training and testing compared to the current model.

Copied to clipboard

Xiusheng Huang, Yubo Chen, Shun Wu, Jun Zhao, Yuantao Xie, Weijian Sun

Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition (2021.emnlp-main)

Challenge:	Existing methods for named entity recognition (NER) do not distinguish noisy from hard samples.
Approach:	They propose a noise-aware-with-filter method to help model identify noisy samples . they propose 'incomplete trust' loss function which boosts L CRF with a robust term .
Outcome:	The proposed method outperforms the existing methods on six real-world Chinese and English NER datasets.

Copied to clipboard

Rui Wang, Ricardo Henao

Attention and Edge-Label Guided Graph Convolutional Networks for Named Entity Recognition (2022.emnlp-main)

Challenge:	Existing methods augment input sequence with token replacement, assuming annotations on the replaced positions are unchanged.
Approach:	They propose to use paraphrasing to enhance unsupervised consistency training by replacing tokens with augmented data.
Outcome:	The proposed method is especially effective when annotations are limited.

Copied to clipboard

Renjie Zhou, Zhongyi Xie, Jian Wan, Jilin Zhang, Yong Liao, Qiang Liu

Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System (2020.coling-main)

Challenge:	Named entity recognition (NER) is the recognition of entities with specific meanings in the text, mainly including person, organization, location, etc.
Approach:	They propose an edge-aware node joint update module and introduce a node-awful edge update module to explore hidden in structured information and solve the wrong dependency label information to some extent.
Outcome:	The proposed model can exploit the structured information on the dependency tree to improve the recognition of long entities.

Copied to clipboard

Hiroaki Takatsu, Ryota Ando, Yoichi Matsuyama, Tetsunori Kobayashi

Joint Multitask Learning for Community Question Answering Using Task-Specific Embeddings (D18-1)

Challenge:	In smart speakers and conversational robots, the demand for expressive speech synthesis has increased.
Approach:	They propose to annotate a news dataset with emotion labels for each sentence and to evaluate its effectiveness using the constructed dataset.
Outcome:	The proposed method improves the performance of the proposed model by preferentially annotating news articles with low confidence in the human-in-the-loop machine learning framework.

Copied to clipboard

Shafiq Joty, Lluís Màrquez, Preslav Nakov

Multi-Grained Knowledge Distillation for Named Entity Recognition (2021.naacl-main)

Challenge:	Stack-Overflow, Quora, and Yahoo! Answers forums are not moderated, which results in noisy and redundant content.
Approach:	They use deep neural networks to learn meaningful task-specific embeddings . they incorporate the embeddables into a conditional random field model .
Outcome:	The proposed task improves significantly across evaluation metrics.

Copied to clipboard

Xuan Zhou, Xiao Zhang, Chenyang Tao, Junya Chen, Bing Xu, Wei Wang, Jing Xiao

Green & Sustainable NLP

Challenge:	Pre-trained big models have delivered top performance in Seq2seq modeling, but their deployments in real-world applications are often hindered by excessive computations and memory demands.
Approach:	They propose a distillation scheme to efficiently transfer knowledge from big models to their cheaper counterparts.
Outcome:	The proposed scheme maximizes the assimilation of knowledge from the teacher model to the student model.

AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network (2020.emnlp-main)

Copied to clipboard

Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Challenge:	Existing approaches to sequence labeling require sequential computation that makes parallelization impossible.
Approach:	They propose to employ a parallelizable approximate variational inference algorithm for the CRF model.
Outcome:	The proposed approach improves decoding speed and accuracy with long sentences and is parallelizable for faster training and prediction.

Simulating ASR errors for training SLU systems (L18-1)

Copied to clipboard

Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève

Phrase Grounding by Soft-Label Chain Conditional Random Field (D19-1)

Challenge:	Existing methods to simulate automatic speech recognition errors from manual transcriptions are not available during training of the SLU model.
Approach:	They propose to use acoustic and linguistic word embeddings to define a similarity measure between words to predict ASR confusions.
Outcome:	The proposed method significantly improves the performance of spoken language understanding systems.

Copied to clipboard

Jiacheng Liu, Julia Hockenmaier

Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning (2020.emnlp-main)

Challenge:	Existing methods to ground entities depend on inference or non-differentiable losses.
Approach:	They propose a phrase grounding task that grounds entities to corresponding regions in an image . they use neural chain Conditional Random Fields to model dependencies among regions .
Outcome:	The proposed method is based on a dataset of the Flickr30k Entities dataset.

Copied to clipboard

Yi Yang, Arzoo Katiyar

Improving Low-Resource Named Entity Recognition using Joint Sentence and Token Labeling (2020.acl-main)

Challenge:	Named entity recognition (NER) is widely adopted in several domains, such as news, medical, and social media.
Approach:	They propose a few-shot named entity recognition system based on nearest neighbor learning and structured inference.
Outcome:	The proposed method improves F1 scores on standard few-shot NER evaluation tasks by 6% to 16% relative to previous methods.

Copied to clipboard

Canasai Kruengkrai, Thien Hai Nguyen, Sharifah Mahani Aljunied, Lidong Bing

Enhancing Deep Learning with Embedded Features for Arabic Named Entity Recognition (2022.lrec-1)

Challenge:	Existing models for named entity recognition (NER) use sentence-level labels, which are expensive to obtain, to improve NER.
Approach:	They propose a sentence-level named entity recognition model that uses sentence-based labels that are easy to obtain.
Outcome:	The proposed model produces 3.78%, 4.20%, 2.08% improvements in F1 over the baseline on e-commerce product titles in Vietnamese, Thai, and Indonesian, respectively.

Copied to clipboard

Ali L. Hatab, Caroline Sabty, Slim Abdennadher

Neural Architectures for Nested NER through Linearization (P19-1)

Challenge:	Word embeddings can capture the semantics of words and other hidden features, but the Arabic language is complex and requires a large amount of information to process.
Approach:	They propose to add morphological and syntactical features to Arabic word embeddings to train the model.
Outcome:	The proposed model outperforms the previous systems to the best of our knowledge.

Copied to clipboard

Jana Straková, Milan Straka, Jan Hajic

Named Entity Recognition

Challenge:	a nested named entity recognition (NER) is a set of entities that can overlap and be labeled with more than one label.
Approach:	They propose two neural network architectures for nested named entity recognition . they propose to model nesting entities as multilabels and predict a sequence-to-sequence problem .
Outcome:	The proposed methods outperform the state-of-the-art on four corpora . the proposed models also improve on the recently published contextual embeddings .

Embeddings for Named Entity Recognition in Geoscience Portuguese Literature (2020.lrec-1)

Copied to clipboard

Bernardo Consoli, Joaquim Santos, Diogo Gomes, Fabio Cordeiro, Renata Vieira, Viviane Moreira

Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records (P19-1)

Challenge:	Named Entity Recognition (NER) is a task within the field of Natural Language Processing that deals with the identification and categorization of Named entities (NEs) in a given text.
Approach:	They propose to use vector and tensor embeddings to train Portuguese Named Entity Recognition (NER) in the Geology domain.
Outcome:	The proposed model achieves state-of-the-art for the Portuguese Geology domain with one of its embeddings.

Copied to clipboard

Max Friedrich, Arne Köhn, Gregor Wiedemann, Chris Biemann

Annotated Corpus of Scientific Conference’s Homepages for Information Extraction (L18-1)

Challenge:	De-identification is the task of detecting protected health information (PHI) in medical text.
Approach:	They propose to create shareable representations of medical text that contain no PHI and can be shared between organizations to create unified datasets for training de-identification models.
Outcome:	The proposed representation allows training a simple LSTM-CRF model to an F1 score of 97.4%.

Copied to clipboard

Piotr Andruszkiewicz, Rafał Hazan

A Semi-Markov Structured Support Vector Machine Model for High-Precision Named Entity Recognition (P19-1)

Challenge:	a corpus of scientific conferences contains homepages with annotations of important information . name of conference, abbreviation, place, submission, notification, camera ready dates are included .
Approach:	They propose a corpus that contains 943 homepages of scientific conferences with annotations of interesting information.
Outcome:	The proposed corpus contains 943 homepages of scientific conferences, 14794 including subpages . the results show that it can be used as a reference data set for this type of task.

Copied to clipboard

Ravneet Arora, Chen-Tse Tsai, Ketevan Tsereteli, Prabhanjan Kambadur, Yi Yang

Semi-Supervised Semantic Dependency Parsing Using CRF Autoencoders (2020.acl-main)

Challenge:	Named entity recognition (NER) is the backbone of many NLP solutions.
Approach:	They propose a neural semi-Markov structured support vector machine model that controls the precision-recall trade-off by assigning weights to different types of errors in the loss-augmented inference during training.
Outcome:	The proposed model achieves better precision-recall trade-off at various precision levels.

Copied to clipboard

Zixia Jia, Youmi Ma, Jiong Cai, Kewei Tu

Graph Based Semi-Supervised Learning Approach for Tamil POS tagging (L18-1)

Challenge:	Semantic dependency parsing allows words to have multiple dependency heads, resulting in graph-structured representations.
Approach:	They propose an approach to semi-supervised learning of semantic dependency parsers based on the CRF autoencoder framework.
Outcome:	The proposed model improves over the baseline model and is arc-factored.

Copied to clipboard

Mokanarangan Thayaparan, Surangika Ranathunga, Uthayasanker Thayasivam

Automatic Labeling of Problem-Solving Dialogues for Computational Microgenetic Learning Analytics (L18-1)

Challenge:	Parts of Speech (POS) tagging is challenging for low resourced languages such as Tamil . low resource Tamil does not have large POS annotated corpus to build good quality POS taggers using supervised machine learning techniques.
Approach:	They propose a graph-based semi-supervised learning approach to classify unlabelled data using a small POS labelled data set.
Outcome:	The proposed method achieves 0.8743 over 0.7333 produced by a CRF tagger for the same limited size corpus.

Copied to clipboard

Yuanliang Meng, Anna Rumshisky, Florence Sullivan

arXivEdits: Understanding the Human Revision Process in Scientific Writing (2022.emnlp-main)

Challenge:	This paper presents a recurrent neural network model to automate the analysis of students' computational thinking in problem-solving dialogue.
Approach:	They propose a recurrent neural network model to automate the analysis of students' computational thinking in problem-solving dialogue.
Outcome:	The proposed model outperforms the baseline model and outperformed the nave model by a large margin.

Copied to clipboard

Chao Jiang, Wei Xu, Samuel Stevens

Challenge:	a new computational framework is developed to study text revision in scientific writing . authors propose a method to extract revision at document-, sentence-, and word-levels .
Approach:	They propose a computational framework for studying text revision in scientific writing . arXivEdits is an annotated corpus of 751 full papers from arX . authors propose to use sentence alignment, fine-grained edits and intents to extract revision .
Outcome:	The proposed framework can be used to study revision in scientific writing.

BiLSTM-CRF for Persian Named-Entity Recognition ArmanPersoNERCorpus: the First Entity-Annotated Persian Dataset (L18-1)

Copied to clipboard

Hanieh Poostchi, Ehsan Zare Borzeshi, Massimo Piccardi

M-CNER: A Corpus for Chinese Named Entity Recognition in Multi-Domains (L18-1)

Challenge:	Named-entity recognition (NER) is a natural language processing component that aims to identify all the "named entities" (NEs) in an unstructured text.
Approach:	They propose a deep learning approach for name-entity recognition in Persian . they publicize an entity-annotated Persian dataset and train word embeddings .
Outcome:	The proposed approach achieves a 77.45% CoNLL F 1 score for Persian NER based on a deep learning architecture and pre-trained word embeddings.

Copied to clipboard

Qi Lu, YaoSheng Yang, Zhenghua Li, Wenliang Chen, Min Zhang

AsNER - Annotated Dataset and Baseline for Assamese Named Entity recognition (2022.lrec-1)

Challenge:	NER is one of the most important natural language processing tasks.
Approach:	They propose to annotate sentences from human-computer interaction, social media, and e-commerce using two rounds of annotation.
Outcome:	The proposed system performs the best on all the data sets.

Copied to clipboard

Dhrubajyoti Pathak, Sukumar Nandi, Priyankoo Sarmah

Neural CRF Model for Sentence Alignment in Text Simplification (2020.acl-main)

Challenge:	Named entity recognition (NER) is a type of annotation that classifies text into predefined classes such as person, location, organization etc.
Approach:	They propose to use a named entity annotation dataset for low resource Assamese language with a baseline NER model.
Outcome:	The proposed dataset is likely to be significant resource for deep neural based Assamese language processing.

Copied to clipboard

Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, Wei Xu

A Collaborative Reasoning Framework Powered by Reinforcement Learning and Large Language Models for Complex Questions Answering over Knowledge Graph (2025.coling-main)

Challenge:	Text simplification systems are based on the quality and quantity of complex-simple sentence pairs extracted by aligning sentences between parallel articles.
Approach:	They propose a neural CRF alignment model which leverages the sequential nature of sentences in parallel documents and utilizes a sentence pair model to capture semantic similarity.
Outcome:	The proposed model outperforms previous work on monolingual sentence alignment task by more than 5 points in F1.

Copied to clipboard

Zhiqiang Zhang, Wen Zhao

SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling (2020.acl-main)

Challenge:	Knowledge Graph Question Answering (KGQA) aims to answer natural language questions by reasoning across multiple triples in knowledge graphs.
Approach:	They propose a collaborative reasoning framework powered by RL and LLMs to answer complex questions based on the knowledge graph.
Outcome:	The proposed model surpasses state-of-the-art models on four datasets.

Copied to clipboard

Luoxin Chen, Weitong Ruan, Xinyue Liu, Jianhua Lu

Automatic Period Segmentation of Oral French (2020.lrec-1)

Challenge:	Empirical studies show that virtual adversarial training (VAT) significantly improves the sequence labeling performance over baselines under supervised and semi-supervised settings.
Approach:	They propose a method which naturally applies VAT to sequence labeling models with conditional random field (CRF) Empirical studies show that SeqVAT significantly improves the sequence labelling performance over baselines under supervised settings, and outperforms state-of-the-art approaches under semi-supervised settings.
Outcome:	Empirical results show that the proposed method outperforms state-of-the-art approaches under semi-supervised settings.

Copied to clipboard

Natalia Kalashnikova, Loïc Grobol, Iris Eshkol-Taravella, François Delafontaine

Speech & Audio in NLP

Challenge:	Analor is a semi-automatic tool for speech segmentation in periods but it only takes into account prosodic characteristics of speech.
Approach:	They propose to use a Fribourg model of macro-syntax to detect periods in syntactic and prosodic terms to develop an automatic tool for automatic segmentation of linguistic units.
Outcome:	The proposed tool is compared with an existing tool Analor which divides speech into smaller segments and that CRF models detect larger segments rather than macro-syntactic periods.

ManNER & ManPOS: Pioneering NLP for Endangered Manchu Language (2024.lrec-main)

Copied to clipboard

Sangah Lee, Sungjoo Byun, Jean Seo, Minha Kang

NER-guided Comprehensive Hierarchy-aware Prompt Tuning for Hierarchical Text Classification (2024.lrec-main)

Challenge:	a new study examines the impact of natural language processing (NLP) on the endangered Manchu language.
Approach:	They propose to use BiLSTM-CRF, BERT, and mBERT to train transformer-based models on Manchu for NER and POS tagging tasks.
Outcome:	The proposed models achieved over 90% F1 score in both NER and POS tasks.

Copied to clipboard

Fuhan Cai, Duo Liu, Zhongqiang Zhang, Ge Liu, Xiaozhe Yang, Xiangzhong Fang