MACHINE LEARNING METHODS

A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus (2024.acl-long)

Challenge:	Current methods for learning human language are too data inefficient to learn it in this way.
Approach:	They propose to train a meta-learning agent in simulation to interact with populations of pre-trained agents, each with their own distinct communication protocol.
Outcome:	The proposed algorithm minimizes the number of on-policy interactions while learning human language while minimizing the number on-political interactions.

Copied to clipboard

Eduard Poesina, Cornelia Caragea, Radu Ionescu

Semantic Text Processing

Challenge:	Natural language inference (NLI) is an actively studied topic serving as a proxy for natural language understanding.
Approach:	They propose to use a Romanian NLI corpus to analyze sentence pairs . they use multiple machine learning methods to establish competitive baselines .
Outcome:	The proposed model improves on the best model by employing a new curriculum learning strategy based on data cartography.

IsOBS: An Information System for Oracle Bone Script (2020.emnlp-demos)

Copied to clipboard

Xu Han, Yuzhuo Bai, Keyue Qiu, Zhiyuan Liu, Maosong Sun

Challenge:	Oracle bone script (OBS) documents are the oldest continuously-used writing system in the world and are important for linguistic and historical research.
Approach:	They construct an information system for OBS to symbolize, serialize, and store OBS data at the character-level using efficient databases and retrieval modules.
Outcome:	The proposed system symbolizes, serializes, and stores OBS data at the character-level, based on efficient databases and retrieval modules.

Improving Cross-domain, Cross-lingual and Multi-modal Deception Detection (2022.acl-srw)

Copied to clipboard

Subhadarshi Panda, Sarah Ita Levitan

Information Retrieval

Challenge:	Deception detection is a deliberate choice to mislead to gain some advantage or avoid some penalty.
Approach:	They propose to use inter-domain distance to identify suitable source domain for a given target domain to improve cross-domain deception classification and to better understand multi-modal deception detection.
Outcome:	The proposed methods will be able to detect deception in cross-domain, cross-lingual and multi-modal settings and will improve multi-modular deception classification.

Conformalized Answer Set Prediction for Knowledge Graph Embedding (2025.naacl-long)

Copied to clipboard

Yuqicheng Zhu, Nico Potyka, Jiarong Pan, Bo Xiong, Yunjie He, Evgeny Kharlamov, Steffen Staab

Semantic Text Processing

Challenge:	Knowledge graph embeddings (KGE) map entities and predicates into numerical vectors, providing non-classical reasoning capabilities based on similarities and analogies between entities and relations.
Approach:	They propose to use knowledge graph embeddings to provide non-classical reasoning capabilities by exploiting similarities and analogies between entities and relations.
Outcome:	The proposed model can generate answer sets with probabilistic guarantees on four benchmark datasets and is scaled well with respect to the difficulty of the query.

Autism Detection in Speech – A Survey (2024.findings-eacl)

Copied to clipboard

Nadine Probol, Margot Mieskes

NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification (2023.acl-short)

Challenge:	a range of studies have been done on autism in voice, speech and language . females are under-researched in the field, and there are few experiments with transformers .
Approach:	They analyse studies of how autism is displayed in voice, speech and language . they define autism and which comorbidities might influence the correct detection .
Outcome:	The authors show that there is already a lot of research on autism in speech, but there are still some shortcomings.

Copied to clipboard

Iyanuoluwa Shode, David Ifeoluwa Adelani, JIng Peng, Anna Feldman

Multilinguality

Challenge:	Africa has over 2000 indigenous languages but they are under-represented in NLP research due to lack of datasets.
Approach:	They propose to use a dataset to classify sentiments for cross-domain adaptation for Nigerian and other African languages.
Outcome:	The proposed dataset compares the performance of cross-domain adaptation from Twitter domain and cross-lingual adaptation from English domain.

Persian Ezafe Recognition Using Transformers and Its Role in Part-Of-Speech Tagging (2020.findings-emnlp)

Copied to clipboard

Ehsan Doostmohammadi, Minoo Nassajian, Adel Rahimi

SetConv: A New Approach for Learning from Imbalanced Data (2020.emnlp-main)

Challenge:	Ezafe is a grammatical particle in some Iranian languages that links two words together but is almost always not indicated in Persian script.
Approach:	They propose to use Persian ezafe to improve part-of-speech tagging by using transformer-based methods to achieve state-of the-art results.
Outcome:	The proposed methods achieve state-of-the-art in the task of ezafe recognition and show that they are not useful to transformer-based methods.

Copied to clipboard

Yang Gao, Yi-Fan Li, Yu Lin, Charu Aggarwal, Latifur Khan

Information Retrieval

Challenge:	Existing methods for classification are biased towards the majority class when the Imbalance Ratio (IR) is high.
Approach:	They propose a set convolution operation and an episodic training strategy to extract a single representative for each class, so that classifiers can later be trained on a balanced class distribution.
Outcome:	The proposed algorithm is permutation-invariant despite the order of inputs and shows superiority on multiple large-scale benchmark text datasets.

Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity (2024.findings-eacl)

Copied to clipboard

Eric Khiu, Hasti Toossi, Jinyu Liu, Jiaxu Li, David Anugraha, Juan Flores, Leandro Roman, A. Seza Doğruöz, En-Shiun Lee

Multilinguality

Challenge:	Existing approaches for predicting the performance of NLP models for low-resource languages (LRLs) focus on high-resourced languages, overlooking LRLs and domain shifts.
Approach:	They investigate the impact of domain similarity on predicting performance of machine translation models in low-resource languages.
Outcome:	The results show that domain similarity has the most important impact on predicting the performance of Machine Translation models.

You Don’t Have Time to Read This: An Exploration of Document Reading Time Prediction (2020.acl-main)

Copied to clipboard

Orion Weller, Jordan Hildebrandt, Ilya Reznik, Christopher Challis, E. Shannon Tass, Quinn Snell, Kevin Seppi

Challenge:	Existing work on reading time prediction has focused on word level only predictions . however, previous work has focused only on word levels .
Approach:	They perform an experiment to examine how different features of text contribute to the time it takes to read, distributing and collecting data from over a thousand participants.
Outcome:	The proposed method combines a large number of machine learning methods with textual and stylistic factors to predict the time it takes to read.

Learning Morphosyntactic Analyzers from the Bible via Iterative Annotation Projection across 26 Languages (P19-1)

Copied to clipboard

Garrett Nicolai, David Yarowsky

Syntactic Text Processing

Challenge:	Currently, computational tools for low-resource languages are limited by a lack of supervised training data.
Approach:	They propose to use English taggers and parsers to project morphological information onto translations of the Bible in 26 different test languages.
Outcome:	The proposed method reduces lemmatization and morphological analysis over a strong initial system.

Academic-Industrial Perspective on the Development and Deployment of a Moderation System for a Newspaper Website (L18-1)

Copied to clipboard

Dietmar Schabus, Marcin Skowron

Challenge:	a system that supports the moderation of user comments on a large newspaper website is described in this paper.
Approach:	They describe an approach and experiences from the development, deployment and usability testing of a natural language processing and information retrieval system that supports the moderation of user comments on a large newspaper website.
Outcome:	The proposed system supports the moderation of user comments on a large newspaper website.

Comparing Machine Learning and Deep Learning Approaches on NLP Tasks for the Italian Language (2020.lrec-1)

Copied to clipboard

Bernardo Magnini, Alberto Lavelli, Simone Magnolini

Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals (2022.acl-long)

Challenge:	Using available datasets, we compare deep learning and traditional machine learning methods for various NLP tasks in Italian.
Approach:	They compare deep learning and traditional machine learning methods for various NLP tasks in Italian.
Outcome:	The proposed methods outperform traditional methods in sequence tagging tasks and classification tasks in Italian.

Copied to clipboard

Te-Lin Wu, Alex Spangher, Pegah Alipoormolabashi, Marjorie Freedman, Ralph Weischedel, Nanyun Peng

A Corpus of Natural Multimodal Spatial Scene Descriptions (L18-1)

Challenge:	Current machine learning methods are incapable of efficiently utilizing multimodal information.
Approach:	They propose to use text-and-image alignment to improve machine learning's performance on multimodal event sequencing.
Outcome:	The proposed models perform significantly worse than humans on multimodal event sequencing than humans.

Copied to clipboard

Ting Han, David Schlangen

Exploiting Careful Design of SVM Solution for Aspect-term Sentiment Analysis (2024.findings-emnlp)

Challenge:	Existing work on multimodal spatial descriptions combines speech and hand gestures to form a corpus of multimodal descriptions.
Approach:	They present a corpus of multimodal spatial descriptions as commonly occurring in route giving tasks.
Outcome:	The proposed corpus of multimodal spatial descriptions is more amenable to computational analysis and useable for learning natural computer interfaces.

Copied to clipboard

Hanfeng Liu, Minping Chen, Zhenya Zheng, Zeyi Wen

Sentiment Analysis

Challenge:	Aspect-term sentiment analysis (ATSA) identifies fine-grained sentiments towards specific aspects of text.
Approach:	They propose a pipeline to predict fine-grained sentiments for specific aspects of text . it decomposes the learning problem into multiple view subproblems and dynamically selects and constructs features with reinforcement learning.
Outcome:	The proposed pipeline surpasses SVM-based methods in predictive accuracy while maintaining a faster inference speed and significantly reducing the number of model parameters.

Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement Patterns (2022.acl-long)

Copied to clipboard

Daniel Wiechmann, Yu Qiao, Elma Kerz, Justus Mattern

Cross-Lingual Cross-Platform Rumor Verification Pivoting on Multimedia Content (D18-1)

Challenge:	Existing work to predict gaze patterns during naturalistic reading has not been conducted on general text characteristics.
Approach:	They propose to use two eye-tracking corpora of naturalistic reading and two language models to test their performance.
Outcome:	The proposed models predict eye-tracking measures during naturalistic reading and language processing.

Copied to clipboard

Weiming Wen, Songwen Su, Zhou Yu

Multilinguality

Challenge:	rumors with multimedia content are becoming more and more common on social networks . a new feature set is proposed to verify rumors pivoting on multimedia content .
Approach:	They propose to use multimedia content to find external information on social media platforms . they propose to leverage semantic similarity between rumors and external information .
Outcome:	The proposed approach achieves state-of-the-art results on social networks . it leverages semantic similarity between rumors and external information .

Detecting Dementia from Long Neuropsychological Interviews (2022.findings-emnlp)

Copied to clipboard

Nauman Dawalatabad, Yuan Gong, Sameer Khurana, Rhoda Au, James Glass

Speech & Audio in NLP

Challenge:	Recent studies suggest examiner's language can influence cognitive impairment classifications.
Approach:	They propose a three-stage pipeline to detect dementia from exam recordings to mitigate the influence of the examiner on automatic dementia identification decisions.
Outcome:	The proposed pipeline mitigates the influence of the examiner on automatic dementia identification decisions in real-world neuropsychological exams.

TRANSLIT: A Large-scale Name Transliteration Resource (2020.lrec-1)

Copied to clipboard

Fernando Benites, Gilbert François Duivesteijn, Pius von Däniken, Mark Cieliebak

Challenge:	Transliteration is the process of expressing a proper name from a source language in the characters of a target language.
Approach:	They present a large-scale corpus of transliterated names in 180 languages . they use machine learning to train automatic transliteration .
Outcome:	The proposed system achieves 92% accuracy on identification of transliterated pairs.

Evaluating Methods for Extraction of Aspect Terms in Opinion Texts in Portuguese - the Challenges of Implicit Aspects (2022.lrec-1)

Copied to clipboard

Mateus Machado, Thiago Alexandre Salgueiro Pardo

CLFD: A Novel Vectorization Technique and Its Application in Fake News Detection (2020.lrec-1)

Challenge:	In aspect-based sentiment analysis, the implicit mention of aspects is difficult to identify and may require world knowledge to do so.
Approach:	They evaluate frequency-based, hybrid, and machine learning methods to extract aspect terms from opinionated texts in Portuguese.
Outcome:	The proposed methods show that they are more efficient and more efficient than previous methods.

Copied to clipboard

Michail Mersinias, Stergos Afantenos, Georgios Chalkiadakis

Responsible & Trustworthy NLP

Challenge:	Existing work on fake news detection is limited due to the complex nature of the news .
Approach:	They propose a statistical approach for the generation of feature vectors to describe a document . they use class label frequency distance to boost machine learning methods .
Outcome:	The proposed method outperforms deep learning methods in large datasets while outperforming traditional methods.

RECAL: Sample-Relation Guided Confidence Calibration over Tabular Data (2023.findings-emnlp)

Copied to clipboard

Wang HaoTian, Zhen Zhang, Mengting Hu, Qichao Wang, Liang Chen, Yatao Bian, Bingzhe Wu

Auto-hMDS: Automatic Construction of a Large Heterogeneous Multilingual Multi-Document Summarization Corpus (L18-1)

Challenge:	Various machine learning methods for tabular data lack accurate confidence estimation, which is needed for high-risk sensitive applications such as credit modeling and financial fraud detection.
Approach:	They propose a general post-training confidence calibration framework to calibrate the confidence of current machine learning models by employing graph neural networks to model the relationships between different samples.
Outcome:	The proposed framework improves the confidence estimation on tabular datasets by using graph neural networks to model the relationships between different samples.

Copied to clipboard

Markus Zopf

Text Generation

Challenge:	Existing datasets for automatic text summarization are small and focused on newswires.
Approach:	They propose to automatically generate a large multilingual multi-document summarization corpus using Wikipedia articles as summaries and to automatically search for appropriate source documents.
Outcome:	The proposed corpus contains 7,316 topics in English and German with different summary lengths and number of source documents.

A Broad-coverage Corpus for Finnish Named Entity Recognition (2020.lrec-1)

Copied to clipboard

Jouni Luoma, Miika Oinonen, Maria Pyykönen, Veronika Laippala, Sampo Pyysalo

Part-of-Speech Tagging for Arabic Gulf Dialect Using Bi-LSTM (L18-1)

Challenge:	Named entity recognition (NER) is a fundamental task in natural language processing (NLP).
Approach:	They propose to annotate Finnish named entity names using a new corpus built on the Universal Dependencies corpus.
Outcome:	The new annotation identifies over 10,000 mentions and maintains compatibility with a previously released single-domain corpus for Finnish NER.

Copied to clipboard

Randah Alharbi, Walid Magdy, Kareem Darwish, Ahmed AbdelAli, Hamdy Mubarak

Syntactic Text Processing

Challenge:	Part-of-speech (POS) tagging is one of the most important building blocks in many natural language processing (NLP) applications.
Approach:	They propose to use a POS tagger for Arabic Gulf dialect to improve POS tagging accuracy.
Outcome:	The proposed POS tagger improves POS tagging accuracy for the Arabic Gulf dialect from 75% accuracy to 91% accuracy using a bi-LSTM labeler.

A Novel Contrastive Learning Method for Clickbait Detection on RoCliCo: A Romanian Clickbait Corpus of News Articles (2023.findings-emnlp)

Copied to clipboard

Daria Broscoteanu, Radu Ionescu

Semantic Text Processing

Challenge:	Clickbait detection is a task that aims to automatically detect misleading news titles . despite the importance of the task, there is no publicly available clickbait corpus for Romanian .
Approach:	They propose a Romanian Clickbait Corpus that automatically detects misleading news titles . they propose four machine learning methods to establish competitive baselines .
Outcome:	The proposed model can learn to encode news titles and contents into a deep metric space . the proposed model is available for download on github.com/dariabroscoteanu/RoCliCo.

LSCP: Enhanced Large Scale Colloquial Persian Language Understanding (2020.lrec-1)

Copied to clipboard

Hadi Abdi Khojasteh, Ebrahim Ansari, Mahdi Bohlouli

Responsible & Trustworthy NLP

Challenge:	a gap exists in describing low-resource formal languages such as Persian . a large scale corpus of 120M sentences is proposed to fill this gap .
Approach:	They propose to target a gap in describing the colloquial language for low-resource ones such as Persian . a large scale Persian corpus is hierarchically organized in a semantic taxonomy .
Outcome:	The proposed corpus consists of 120M sentences from 27M tweets annotated with parsing tree, part-of-speech tags, sentiment polarity and translation in five different languages.

Incorporating Word-level Phonemic Decoding into Readability Assessment (2024.lrec-main)

Copied to clipboard

Christine Pinney, Casey Kennington, Maria Soledad Pera, Katherine Landau Wright, Jerry Alan Fails

Syntactic Text Processing

Challenge:	a recent study suggests that automatic readability assessment is not able to provide interpretability for teachers and educators.
Approach:	They propose to incorporate phonetic and orthographic features into automatic readability assessment by handcrafted feature sets.
Outcome:	a new feature set shows comparable performance to larger feature sets on grade-level classification in english . authors say the model improves on multiple readability datasets but lacks interpretability .

DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition (2025.emnlp-main)

Copied to clipboard

Hanjun Luo, Yingbin Jin, Yiran Wang, Xinfeng Li, Tong Shang, Xuecheng Liu, Ruizhe Chen, Kun Wang, Hanan Salam, Qingsong Wen, Zuozhu Liu

Polish-ASTE: Aspect-Sentiment Triplet Extraction Datasets for Polish (2024.lrec-main)

Challenge:	Existing datasets designed for Named Entity Recognition methods are inadequate for LLMs.
Approach:	They propose a dataset that is multilingual and multi-granular and enables LLMs to be applied to Named Entity Recognition methods.
Outcome:	The proposed dataset is multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains.

Copied to clipboard

Marta Lango, Borys Naglik, Mateusz Lango, Iwo Naglik

Sentiment Analysis

Challenge:	Aspect-Sentiment Triplet Extraction (ASTE) is one of the most challenging and complex tasks in sentiment analysis.
Approach:	They propose to use customer opinions of hotels and purchased products in Polish to extract ASTE triplets that contain an aspect, its associated sentiment polarity, and an opinion phrase that serves as a rationale for the assigned polarities.
Outcome:	The proposed datasets contain customer opinions about hotels and purchased products expressed in Polish and are available under a permissive licence and have the same file format as the English datasets.

Exploring Large Language Models for Detecting Mental Disorders (2025.emnlp-main)

Copied to clipboard

Gleb Kuzmin, Petr Strepetov, Maksim Stankevich, Natalia Chudova, Artem Shelmanov, Ivan Smirnov