SEMI-SUPERVISED LEARNING

Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs (2020.acl-main)

Challenge:	Manually labeled training data is expensive, noisy, and often scarce . semi-supervised learning methods can be used to improve model performance .
Approach:	They explore different methods for consistency training on unlabeled data . they use human paraphrasing, back-translation, and dropout to augment unlabed data.
Outcome:	The proposed methods outperform purely supervised learning on unlabeled data.

Copied to clipboard

Dong Bok Lee, Seanie Lee, Woo Tae Jeong, Donghwan Kim, Sung Ju Hwang

Question Answering

Challenge:	Existing models for question answering are limited in the availability of labeled data.
Approach:	They propose a hierarchical conditional variational autoencoder for generating QA pairs given unstructured texts as contexts while maximizing mutual information between generated QA pair to ensure consistency.
Outcome:	The proposed framework achieves impressive performance gains over baseline models on both tasks, using only a fraction of data for training.

Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder (2020.acl-srw)

Copied to clipboard

Zheng Tang, Gus Hahn-Powell, Mihai Surdeanu

T2NER: Transformers based Transfer Learning Framework for Named Entity Recognition (2021.eacl-demos)

Challenge:	EE is a key requirement for machine learning in many domains, e.g., legal, medical, finance.
Approach:	They propose an interpretable approach for event extraction that jointly trains a classifier and a rule decoder for event processing.
Outcome:	The proposed approach can be used for semi-supervised learning and its performance improves when trained on automatically-labeled data generated by a rule-based system.

Copied to clipboard

Saadullah Amin, Guenter Neumann

Combining Weakly Supervised ML Techniques for Low-Resource NLU (2021.naacl-industry)

Challenge:	Named entity recognition (NER) is an important task in information extraction due to large variations in entity names and flexibility in how entities are mentioned.
Approach:	They propose a Transformers based Transfer Learning framework for Named Entity Recognition (T2NER) that integrates transformer models with the state-of-the-art in NLP and provides a unified platform for transfer learning.
Outcome:	The proposed framework bridges the gap between the state-of-the-art in transformer models and the state of the art in NER with deep transformer models.

Copied to clipboard

Victor Soto, Konstantine Arkoudas

ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization (2020.emnlp-main)

Challenge:	Recent advances in transfer learning have improved the performance of virtual assistants . however, meager training data is often a key bottleneck in creating voice-enabled applications .
Approach:	They propose to use unsupervised and semi-supervised techniques to improve NLU accuracy . they incorporate anonymized, unlabeled and automatically transcribed user utterances into training .
Outcome:	The proposed methods improve NLU accuracy in low-resource settings by integrating unsupervised and SSL techniques.

Copied to clipboard

Shiyue Zhang, Benjamin Frey, Mohit Bansal

Multilinguality

Challenge:	Cherokee is a highly endangered Native American language spoken by the Cherokee people . there are only 2,000 fluent first language Cherokee speakers remaining in the world .
Approach:	They propose a Cherokee-English parallel dataset to facilitate machine translation between Cherokee and English.
Outcome:	The proposed dataset compares Cherokee-English and English-Cherokee machine translation systems . the results show that the datasets are low-resource and low-cost compared to other datasets .

Leveraging Moment Injection for Enhanced Semi-supervised Natural Language Inference with Large Language Models (2025.naacl-short)

Copied to clipboard

Seo Yeon Park

Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift (N18-2)

Challenge:	Existing studies have used class-specific fine-tuned large language models to generate hypotheses and assign pseudo-labels but discarded many LLM-constructed samples to ensure the quality.
Approach:	They propose to leverage LLM-constructed samples by injecting the moments of labeled samples during training to properly adjust the level of noise.
Outcome:	The proposed method outperforms strong baselines on multiple NLI datasets in low-resource settings.

Copied to clipboard

Ajay Nagesh, Mihai Surdeanu

Scalable Prompt Generation for Semi-supervised Learning with Language Models (2023.findings-eacl)

Challenge:	Using ladder networks, semi-supervised learning can be iterative and drifts semantically as learning progresses.
Approach:	They propose a method that uses ladder networks to perform a task of named entity classification using a large, unannotated dataset.
Outcome:	The proposed method improves on two standard datasets for named entity classification.

Copied to clipboard

Yuhang Zhou, Suraj Maharjan, Beiye Liu

Semi-supervised Relation Extraction via Data Augmentation and Consistency-training (2023.eacl-main)

Challenge:	Prompt-based learning methods in semi-supervised learning (SSL) settings have been shown to be effective on multiple natural language understanding datasets and tasks.
Approach:	They propose to use a set of prompt tokens to create diverse prompt models and a varying number of soft prompt token to encourage language models to learn different prompts.
Outcome:	The proposed method achieves the best average accuracy of 71.5% in different few-shot learning settings.

Copied to clipboard

Komal Teru

VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation (2021.acl-long)

Challenge:	Obtaining high-quality human labelled data is an expensive and noisy process.
Approach:	They propose to leverage unlabelled data to improve the sample efficiency of the models.
Outcome:	The proposed methods can be used to extract the Cause-Effect relation between a given head entity and tail entity based on context in the input sentence.

Copied to clipboard

Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux

Semi-Supervised Semantic Role Labeling with Cross-View Training (D19-1)

Challenge:	VoxPopuli provides 400K hours of unlabeled speech data in 23 languages . large amounts of multilingual audio data are needed to achieve similar progress for multilingual ASR and ST.
Approach:	They propose a large-scale multilingual corpus that provides 400K hours of unlabeled speech data in 23 languages.
Outcome:	The proposed corpus provides 400K hours of unlabeled speech data in 23 languages and 1.8K hours transcribed speeches in 15 languages and their aligned oral interpretations into 15 target languages totaling 17.3K hours.

Copied to clipboard

Rui Cai, Mirella Lapata

Unraveling the Dynamics of Semi-Supervised Hate Speech Detection: The Impact of Unlabeled Data Characteristics and Pseudo-Labeling Strategies (2024.findings-eacl)

Challenge:	Recent approaches rely on expensive annotations and are unavailable in low resource scenarios (e.g., rare languages or domains).
Approach:	They propose an end-to-end SRL model which leverages unlabeled data and propose to reduce the annotation effort involved via semi-supervised learning.
Outcome:	The proposed model outperforms the state-of-the-art in English and consistently improves performance in other languages, including Chinese, German, and Spanish.

Copied to clipboard

Florian Ludwig, Klara Dolos, Ana Alves-Pinto, Torsten Zesch

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

Challenge:	Semi-supervised learning addresses the need for large amounts of labeled training data for state-of-the-art approaches.
Approach:	They propose to leverage unlabeled data to reduce the amount of annotated data required for machine learning based hate speech detection by using a semi-supervised approach.
Outcome:	The proposed approach reduces the amount of annotated data required by state-of-the-art models by leveraging unlabeled data.

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.

Semi-Supervised Tri-Training for Explicit Discourse Argument Expansion (2020.lrec-1)

Copied to clipboard

René Knaebel, Manfred Stede

MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification (2025.emnlp-main)

Challenge:	a novel application of semi-supervision for shallow discourse parsing is described . we focus on explicit discourse arguments, but we leave the sense selection aside .
Approach:	They propose a semi-supervised approach for shallow discourse parsing using sequence tagging.
Outcome:	The proposed approach improves performance by 2-10% in the first setting and by comparing the results with training relations.

Copied to clipboard

Iustin Sirbu, Robert-Adrian Popovici, Cornelia Caragea, Stefan Trausan-Matu, Traian Rebedea

Co-training for Low Resource Scientific Natural Language Inference (2024.acl-long)

Challenge:	MultiMatch is a semi-supervised learning (SSL) algorithm that combines co-training and consistency regularization with pseudo-labeling.
Approach:	They propose a semi-supervised learning algorithm that integrates co-training and consistency regularization with pseudo-labeling.
Outcome:	The proposed algorithm outperforms the second-best approach on 8 out of 10 setups from 5 natural language processing datasets and outperformed the second best by 3.26%.

Copied to clipboard

Mobashir Sadat, Cornelia Caragea

Exploiting Labeled and Unlabeled Data via Transformer Fine-tuning for Peer-Review Score Prediction (2022.findings-emnlp)

Challenge:	Scientific Natural Language Inference (NLI) is a task to predict the semantic relation between sentences extracted from research articles.
Approach:	They propose a co-training method that assigns weights based on the training dynamics of the classifiers to the distantly supervised labels.
Outcome:	The proposed method achieves an improvement of 1.5% in Macro F1 over the distant supervision baseline and substantial improvements over several other strong SSL baselines.

Copied to clipboard

Panitan Muangkammuen, Fumiyo Fukumoto, Jiyi Li, Yoshimi Suzuki

Multi-Task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces (N18-1)

Challenge:	Existing work on automatic peer-review aspect score prediction rely on limited data sets.
Approach:	They propose a semi-supervised learning method that incorporates the Transformer fine-tuning into the -model to leverage contextual features from unlabeled data.
Outcome:	The proposed method outperforms supervised and naive methods in the peer-review dataset.

Copied to clipboard

Isabelle Augenstein, Sebastian Ruder, Anders Søgaard

GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples (2020.acl-main)

Challenge:	Multi-task learning and semi-supervised learning are successful paradigms for learning in scenarios with limited labelled data.
Approach:	They propose to induce a joint embedding space between disparate label spaces and learning transfer functions between label embeddments to leverage unlabelled data and auxiliary, annotated datasets.
Outcome:	The proposed approach outperforms strong single and multi-task baselines and achieves state of the art on aspect-based and topic-based sentiment analysis.

Copied to clipboard

Danilo Croce, Giuseppe Castellucci, Roberto Basili

P-Stance: A Large Dataset for Stance Detection in Political Domain (2021.findings-acl)

Challenge:	Recent Transformer-based architectures provide impressive results in many NLP tasks, but obtaining high-quality annotated data is expensive and time consuming.
Approach:	They propose a semisupervised learning method that ex- tends the fine-tuning of BERT-like architectures with unlabeled data in a generative adversarial setting.
Outcome:	The proposed method reduces the requirement for annotated examples while achieving good performance in sentence classification tasks.

Copied to clipboard

Yingjie Li, Tiberiu Sosea, Aditya Sawant, Ajith Jayaraman Nair, Diana Inkpen, Cornelia Caragea

Sentiment Analysis

Challenge:	stance detection is a method to determine whether a text author is in favor of, against or neutral toward a specific target.
Approach:	They propose to use a large stance detection dataset in the political domain to detect stances on twitter.
Outcome:	The proposed model achieves a macro-average F1-score of 80.53% and can be used to improve cross-domain stance detection.

Progressive Class Semantic Matching for Semi-supervised Text Classification (2022.naacl-main)

Copied to clipboard

Haiming Xu, Lingqiao Liu, Ehsan Abbasnejad

Learning from Executions for Semantic Parsing (2021.naacl-main)

Challenge:	Recent semi-supervised learning methods have achieved impressive performance . semi-controlled learning can be used to reduce the annotation cost of text classifiers .
Approach:	They propose a semi-supervised learning process that builds a standard K-way classifier and a matching network for the input text and the Class Semantic Representation (CSR).
Outcome:	The proposed method improves baselines and overall is more stable.

Copied to clipboard

Bailin Wang, Mirella Lapata, Ivan Titov

Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction (2020.emnlp-main)

Challenge:	Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs.
Approach:	They propose to encourage a parser to generate executable programs for unlabeled NL utterances.
Outcome:	The proposed training objectives outperform conventional methods on Overnight and GeoQuery.

Copied to clipboard

Xu Zhao, Zihao Wang, Hao Wu, Yong Zhang

Multilinguality

Challenge:	Existing semisupervised methods do not fully utilize the knowledge hidden in annotated and nonannotated data, which hinders further improvement of their performance.
Approach:	They propose a semi-supervised BLI framework to encourage interaction between supervised signal and unsupervised alignment.
Outcome:	The proposed framework can incorporate any supervised and unsupervised BLI methods based on optimal transport and bi-directional lexicon update.

DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining (2023.emnlp-main)

Copied to clipboard

Weifeng Jiang, Qianren Mao, Chenghua Lin, Jianxin Li, Ting Deng, Weiyi Yang, Zheng Wang

Adversarial Domain Adaptation for Machine Reading Comprehension (D19-1)

Challenge:	Existing text mining models are fine-tuned by fine-timing a large pre-trained language model (PLM) in downstream tasks.
Approach:	They propose a semi-supervised learning framework for fine-tuning a cohort of small student models generated from a large pre-trained language model using knowledge distillation.
Outcome:	The proposed framework outperforms baseline models on semi-supervised text classification and extractive summarization tasks while maintaining comparable performance.

Copied to clipboard

Huazheng Wang, Zhe Gan, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Hongning Wang

Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout (N19-1)

Challenge:	Existing models for machine reading comprehension rely on large amounts of human-annotated in-domain data.
Approach:	They propose an unsupervised domain adaptation framework for Machine Reading Comprehension where the source domain has a large amount of labeled data, while only unlabeled passages are available in the target domain.
Outcome:	The proposed framework can be generalizable to different MRC models and datasets and can be extended to semi-supervised learning.

Copied to clipboard

Hao Tan, Licheng Yu, Mohit Bansal

Machine Translation

Challenge:	Existing approaches perform significantly worse in unseen environments compared to seen ones.
Approach:	They propose to use a ‘environmental dropout’ method to generate unseen triplets to generate new paths and instructions to generalize the agent.
Outcome:	The proposed agent outperforms the state-of-the-art approaches on the private unseen test set and is ranked top on the leaderboard.

Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence (2025.findings-naacl)

Copied to clipboard

Qianren Mao, Weifeng Jiang, Junnan Liu, Chenghua Lin, Qian Li, Xianqing Wen, Jianxin Li, Jinhu Lu

CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning (2021.emnlp-main)

Challenge:	Existing frameworks for semi-supervised text mining with lightweight models are limited by label data scarcity.
Approach:	They propose a framework for semi-supervised text mining with lightweight models . it incorporates online distillation to train lightweight student models by imitating the Teacher model .
Outcome:	The proposed framework exhibits notable performance enhancements over existing frameworks.

Copied to clipboard

Zhenxi Lin, Qianli Ma, Jiangyue Yan, Jieyu Chen

Semi-Supervised Domain Adaptation for Emotion-Related Tasks (2023.findings-acl)

Challenge:	Existing models for metaphor detection require a large amount of labeled data and are not linguistically-based.
Approach:	They propose a ContrAstive pre-Trained modEl (CATE) for metaphor detection with semi-supervised learning using a pre-trained model to obtain a contextual representation of target words.
Outcome:	The proposed model outperforms existing models on several benchmark datasets and achieves better performance against state-of-the-art models.

Copied to clipboard

Mahshid Hosseini, Cornelia Caragea

Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection (2024.naacl-long)

Challenge:	Semi-supervised domain adaptation (SSDA) is a model trained from a label-rich source domain to a new but related domain with a few labels of target data.
Approach:	They propose to decompose the semi-supervised domain adaptation framework into two subcomponents of unsupervised domain adaption (UDA) from the source to the target domain and semi-supervised learning (SSL) in the target.
Outcome:	The proposed method is based on the co-learning of multiple classifiers for computer vision tasks and is published in the journal Nature.

Copied to clipboard

Jianfeng He, Hang Su, Jason Cai, Igor Shalyminov, Hwanjun Song, Saab Mansour

Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification (D18-1)

Challenge:	Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data.
Approach:	They propose a scoring approach that encapsulates three primary dimensions of summarization model quality.
Outcome:	The proposed method reduces reliance on human-labeled data and improves the performance of summarization models.

Copied to clipboard

Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier

Improving Limited Labeled Dialogue State Tracking with Self-Supervision (2020.findings-emnlp)

Challenge:	Existing methods for cross-domain sentiment classification are difficult and costly . domain adaptation is difficult because data in source and target domains are drawn from different distributions.
Approach:	They propose a semi-supervised learning approach that minimizes the distance between source and target instances in embedded feature space.
Outcome:	The proposed approach can improve on baseline methods in various settings.

Copied to clipboard

Chien-Sheng Wu, Steven C.H. Hoi, Caiming Xiong

Semi-Supervised Data Programming with Subset Selection (2021.findings-acl)

Challenge:	Existing dialogue state tracking models require plenty of labeled data, but collecting labels is expensive.
Approach:	They propose to use only 1% labeled data to train dialogue state tracking models . they encourage a model to have consistent latent distributions given a perturbed input .
Outcome:	The proposed self-supervised signals improve goal accuracy by 8.95% when only 1% labeled data is used on the MultiWOZ dataset.

Copied to clipboard

Ayush Maheshwari, Oishik Chatterjee, Krishnateja Killamsetty, Ganesh Ramakrishnan, Rishabh Iyer

WARM: A Weakly (+Semi) Supervised Math Word Problem Solver (2022.coling-1)

Challenge:	Several approaches to improve annotation cost have been proposed to use large amounts of labelled training data.
Approach:	They propose a semi-supervised data programming paradigm that uses weak supervision and semi-supervised loss functions to augment small amounts of labelled data with a large unlabelled dataset.
Outcome:	The proposed framework outperforms the current state-of-the-art on seven publicly available datasets.

Copied to clipboard

Oishik Chatterjee, Isha Pandey, Aashish Waikar, Vishwajeet Kumar, Ganesh Ramakrishnan

Self-training Improves Pre-training for Natural Language Understanding (2021.naacl-main)

Challenge:	Existing approaches to solving math word problems require full supervision in the form of intermediate equations.
Approach:	They propose a weakly supervised model that requires only the final answer as supervision to solve math word problems.
Outcome:	The proposed model achieves accuracy gains of 4.5% and 32% over current weakly-supervised methods on standard Math23K and AllArith datasets.

Copied to clipboard

Jingfei Du, Edouard Grave, Beliz Gunel, Vishrav Chaudhary, Onur Celebi, Michael Auli, Veselin Stoyanov, Alexis Conneau

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

Challenge:	Unsupervised pretraining has led to improvements in natural language understanding . a data augmentation method can be used to generate labels for unlabeled examples .
Approach:	They propose a semi-supervised method which uses unlabeled data to retrieve sentences from a database of billions of unlabed sentences crawled from the web.
Outcome:	The proposed method improves on standard text classification benchmarks by 2.6% and knowledge distillation by few shots.

Copied to clipboard

Rui Wang, Ricardo Henao

JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification (2023.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

Henry Zou, Cornelia Caragea

SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training (2022.findings-emnlp)

Challenge:	Existing approaches to semi-supervised text classification suffer from pseudo-label bias and error accumulation.
Approach:	They propose a pseudo-labeling approach to semi-supervised text classification that unifies ideas from semi-semi-supervised learning and the task of learning with noise.
Outcome:	The proposed approach achieves a significant improvement on benchmark datasets even in the extremely-scarce-label setting.

Copied to clipboard

Hui Chen, Wei Han, Soujanya Poria

Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing (2022.coling-1)

Challenge:	Existing methods for semi-supervised text classification have shown great performance in few-shot scenarios, where both labeled and unlabeled data are utilized.
Approach:	They propose a simple instance-adaptive self-training method for semi-supervised text classification that generates two augmented views for each unlabeled data and trains a meta learner to identify relative strength of augmentations based on the similarity between the original view and the augmented view.
Outcome:	The proposed method consistently shows competitive performance with varying sizes of labeled training data compared to existing semi-supervised learning methods.

Copied to clipboard

Yuanhe Tian, Yan Song, Fei Xia

Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding (2023.findings-emnlp)

Challenge:	Dependency parsing is an important natural language processing task which analyzes the syntactic structure of an input sentence.
Approach:	They propose a structure-aware encoder pre-trained on auto-parsed data to improve dependency parsing . they propose combining gold dependency trees with existing parsers to improve parser performance .
Outcome:	The proposed approach outperforms baselines under different parsers and dependency standards under different parameters and model architectures.

Copied to clipboard

Jianing Wang, Qiushi Sun, Nuo Chen, Chengyu Wang, Jun Huang, Ming Gao, Xiang Li

Unsupervised Data Augmentation for Aspect Based Sentiment Analysis (2022.coling-1)

Challenge:	Existing methods for pre-trained language models rely on noisy data, which can be expensive if all parameters are updated.
Approach:	They propose a self-training framework that incorporates Monte Carlo dropouts into the model and judiciously selects reliable pseudo-labeled examples based on confidence and certainty.
Outcome:	The proposed framework improves performance and efficiency over multiple tasks over multiple datasets.

Copied to clipboard

David Z. Chen, Adam Faulkner, Sahil Badyal

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

Challenge:	Recent approaches to Aspect-based Sentiment Analysis (ABSA) perform the subtasks of aspect term extraction (ATE) and aspect sentiment classification (ASC) simultaneously.
Approach:	They introduce an adaptation of Unsupervised Data Augmentation in semi-supervised learning that performs both aspects of Aspect-based Sentiment Analysis (ABSA) and aspect sentiment classification (ASC) they show that simple augmentations applied to modest-sized datasets along with consistency training lead to competitive performance with current ABSA state-of-the-art in restaurant and laptop domains .
Outcome:	The proposed approach performs well on a span-level classification task with minimal training data.

Copied to clipboard

Mokanarangan Thayaparan, Surangika Ranathunga, Uthayasanker Thayasivam

GunStance: Stance Detection for Gun Control and Gun Regulation (2024.acl-long)

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

Nikesh Gyawali, Iustin Sirbu, Tiberiu Sosea, Sarthak Khanal, Doina Caragea, Traian Rebedea, Cornelia Caragea

Sentiment Analysis

Challenge:	Social media, especially Twitter, has been a melting pot for such debates.
Approach:	They propose to annotate tweets relevant to shooting events into three classes: In-Favor, Against, and Neutral.
Outcome:	The proposed approach outperforms supervised, semi-supervised, and LLM-based zero-shot models on the dataset.

Context-based Virtual Adversarial Training for Text Classification with Noisy Labels (2022.lrec-1)

Copied to clipboard

Do-Myoung Lee, Yeachan Kim, Chang gyun Seo

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning (2020.emnlp-main)

Challenge:	Recent studies show that deep neural networks can memorize noisy labels with limited training time.
Approach:	They propose a virtual adversarial training method to prevent a classifier from overfitting to noisy labels.
Outcome:	The proposed method performs the adversarial training in the context rather than the inputs.

Copied to clipboard

Yichi Zhang, Zhijian Ou, Min Hu, Junlan Feng

Revisiting Tri-training of Dependency Parsers (2021.emnlp-main)

Challenge:	Structured belief states are crucial for goal tracking and database query in task-oriented dialog systems.
Approach:	They propose a probabilistic dialog model where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs.
Outcome:	The proposed model outperforms supervised-only and semi-supervised baselines on three benchmark datasets.

Copied to clipboard

Joachim Wagner, Jennifer Foster

Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP (2021.emnlp-main)

Challenge:	Pre-trained word embeddings and self-training have been used in dependency parsing tasks for years.
Approach:	They compare tri-training and pretrained word embeddings in dependency parsing . they use language-specific FastText and ELMo embedds and multilingual BERT embedders .
Outcome:	The proposed methods are tri-training and pretrained word embeddings.

Copied to clipboard

Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schoelkopf

Challenge:	a meta-analysis of published studies shows that the causal direction of data collection can explain some trends in NLP . semi-supervised learning and domain adaptation performance differ on a number of tasks .
Approach:	They argue that the causal direction of the data collection process has nontrivial implications . authors categorize common NLP tasks according to their causal direction . they also empirically assay the validity of the ICM principle for text data .
Outcome:	The proposed model can explain differences in semi-supervised learning and domain adaptation performance across settings.

Emotion analysis and detection during COVID-19 (2022.lrec-1)

Copied to clipboard

Tiberiu Sosea, Chau Pham, Alexander Tekle, Cornelia Caragea, Junyi Jessy Li

Sentiment Analysis

Challenge:	3,000 English tweets labeled with emotions are used to predict emotions during crises . authors propose semi-supervised learning to bridge this gap .
Approach:	They propose to use a dataset of 3,000 English tweets labeled with emotions . they propose semi-supervised learning to bridge this gap by analyzing unlabeled data .
Outcome:	The proposed model can be used to predict emotions in the context of COVID-19 . the proposed model performs better than other models using unlabeled data .

XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words (2023.findings-emnlp)

Copied to clipboard

Robin Algayres, Pablo Diego-Simon, Benoît Sagot, Emmanuel Dupoux

Multimodality

Challenge:	a new method to segment speech into words is needed to overcome the lack of explicit word boundaries in the speech stream.
Approach:	They propose to fine-tune a self-supervised speech model to predict word boundaries . they use XLS-R to fine tune the models and infer new word boundary labels .
Outcome:	The proposed model outperforms existing models and sets a new state-of-the-art on five corpora with different languages.

Lˆ2GC:Lorentzian Linear Graph Convolutional Networks for Node Classification (2024.lrec-main)

Copied to clipboard

Qiuyu Liang, Weihua Wang, Feilong Bao, Guanglai Gao

More Than Spoken Words: Nonverbal Message Extraction and Generation (2023.emnlp-main)

Challenge:	Existing linear GCNs perform neural network operations in Euclidean space, which do not capture tree-like hierarchical structure of graphs.
Approach:	They propose a Lorentzian linear GCN framework that maps features into hyperbolic space and performs a feature transformation to capture the underlying tree-like structure of data.
Outcome:	The proposed framework achieves state-of-the-art accuracy on standard citation networks datasets and 81.3% on PubMed datasets.

Copied to clipboard

Dian Yu, Xiaoyang Wang, Wanshun Chen, Nan Du, Longyue Wang, Haitao Mi, Dong Yu

VerifyMatch: A Semi-Supervised Learning Paradigm for Natural Language Inference with Confidence-Aware MixUp (2024.emnlp-main)

Challenge:	Existing studies focus on extracting NMs from small-scale well-structured corpora such as movie scripts wherein NM is enclosed in parentheses by scriptwriters, which greatly decreases the difficulty of extraction.
Approach:	They propose to extract nonverbal messages (NMs) from written text and NMs from spoken text by using a semi-supervised learning algorithm.
Outcome:	The extracted NMs can generate more relevant, valid, and factually consistent NM than the purely supervised generator.

Copied to clipboard

Seo Yeon Park, Cornelia Caragea

Reasoning

Challenge:	Natural language inference (NLI) is a key task for evaluating a model's ability to perform natural language understanding and reasoning.
Approach:	They propose to construct pseudo-generated samples using class-specific fine-tuned large language models (LLMs) . they retain all pseudo-labeled samples, but use MixUp to ensure unlabele .
Outcome:	The proposed approach achieves competitive accuracy compared to strong baselines for NLI datasets in low-resource settings.

Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling (2026.findings-acl)

Copied to clipboard

Xingyuan Li, Mengyue Wu

SuperST: Superficial Self-Training for Few-Shot Text Classification (2024.lrec-main)

Challenge:	Existing methods for learning from weakly-supervised speech data are hampered by severe data scarcity and the subjective nature of clinical annotations.
Approach:	They propose a framework that explicitly models pathological traits by jointly learning from frame-level, segment-level and session-level representations within unsegmented clinical dialogues.
Outcome:	The proposed framework is model-agnostic, robust across languages and conditions, and highly data-efficient.

Copied to clipboard

Ju-Hyoung Lee, Joonghyuk Hahn, Hyeon-Tae Seo, Jiho Park, Yo-Sub Han

LLM-Guided Co-Training for Text Classification (2025.emnlp-main)

Challenge:	In few-shot text classification, self-training relies on pseudo-labels to expand data, which has shown success, but can accumulate errors due to noisy pseudo-labeled data.
Approach:	They propose a method to mitigate noise in noisy pseudo-labeled data by applying superficial learning to noisy data and fine-tuning to less noisy data.
Outcome:	The proposed framework improves the classifier accuracy for few-shot text classification by 18.5% at most and 8% in average, compared with the state-of-the-art SSL baselines.

Copied to clipboard

Md Mezbaur Rahman, Cornelia Caragea

Many-Shot Scaling of In-Context Learning with Self-Generated Demonstrations (2026.findings-acl)

Challenge:	Empirical results show that it achieves state-of-the-art performance on 4 out of 5 benchmark datasets and ranks first among 14 compared methods according to the Friedman test.
Approach:	They propose a weighted co-training approach that is guided by Large Language Models (LLMs) they use LLM labels on unlabeled data as target labels and co-train two encoder-only based networks that train each other over multiple iterations.
Outcome:	The proposed approach outperforms conventional methods on 4 out of 5 benchmark datasets and ranks first among 14 compared methods according to the Friedman test.

Copied to clipboard

Zhengyao Gu, Henry Peng Zou, Yankai Chen, Aiwei Liu, Weizhi Zhang, Philip S. Yu