DOWNSTREAM NLP TASKS

Meaning Representations for Natural Languages: Design, Models and Applications (2024.lrec-tutorials)

Challenge:	Cantonese is an influential Chinese variant with a large population of speakers worldwide.
Approach:	This tutorial will review Cantonese's progress in linguistics and NLP . it will introduce transformer-based pre-training methods for a wide range of downstream tasks .
Outcome:	This tutorial will present the main challenges for Cantonese NLP in relation to Cantonesian language idiosyncrasies of colloquialism and multilingualism.

Copied to clipboard

Julia Bonn, Jeffrey Flanigan, Jan Hajič, Ishan Jindal, Yunyao Li, Nianwen Xue

Finite-state script normalization and processing utilities: The Nisaba Brahmic library (2021.eacl-demos)

Challenge:	a tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation.
Approach:	This tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation. authors propose a cutting-edge, full-day tutorial for all stakeholders in the AI community.
Outcome:	This tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation models . it also reviews the applications of meaning representation in downstream NLP tasks and real-world applications .

Copied to clipboard

Cibu Johny, Lawrence Wolf-Sonkin, Alexander Gutkin, Brian Roark

Challenge:	a library for low-level processing of brahmic scripts is available for free.
Approach:	They propose an open-source library for efficient low-level processing of ten major South Asian Brahmic scripts.
Outcome:	The proposed library supports low-level processing of ten major south Asian Brahmic scripts.

Transfer Learning in Natural Language Processing (N19-5)

Copied to clipboard

Sebastian Ruder, Matthew E. Peters, Swabha Swayamdipta, Thomas Wolf

TaxFree: a Visualization Tool for Candidate-free Taxonomy Enrichment (2022.aacl-demo)

Challenge:	supervised machine learning is based on learning in isolation, a single predictive model for a task using a dataset.
Approach:	They present an overview of modern transfer learning methods in natural language processing . they review examples and case studies on how models can be integrated and adapted .
Outcome:	The proposed methods improve upon the state-of-the-art on a wide range of NLP tasks.

Copied to clipboard

Irina Nikishina, Ivan Andrianov, Alsu Vakhitova, Alexander Panchenko

Challenge:	In this paper, we present an open source system for taxonomy visualisation and automatic taxonomies enrichment without pre-defined candidates.
Approach:	They propose an open source system for taxonomy visualisation and automatic taxonomie enrichment without pre-defined candidates on the example of WordNet-3.0.
Outcome:	The proposed system can be used for visualisation and inspection of taxonomies without pre-defined candidates on WordNet-3.0.

Language Identification and Named Entity Recognition in Hinglish Code Mixed Tweets (P18-3)

Copied to clipboard

Kushagra Singh, Indira Sen, Ponnurangam Kumaraguru

Exploring Universal Sentence Encoders for Zero-shot Text Classification (2022.aacl-short)

Challenge:	Named Entity Recognition (NER) is an important text analysis task . code-mixing occurs when lexical items and grammatical features from two languages appear in one sentence .
Approach:	They propose to use language identifiers, parts-of-speech tags and chunkers to analyze code-mixed data.
Outcome:	The proposed method outperforms the best baseline by 33.18%.

Copied to clipboard

Souvika Sarkar, Dongji Feng, Shubhra Kanti Karmaker Santu

Paraphrasing with Large Language Models (D19-56)

Challenge:	Universal Sentence Encoder (USE) has gained popularity as a general-purpose sentence encoding technique.
Approach:	They propose to use Universal Sentence Encoder (USE) to learn a general-purpose sentence encoding technique.
Outcome:	The proposed technique outperforms topic-based inference in zero-shot text classification tasks.

Copied to clipboard

Sam Witteveen, Martin Andrews

Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction (2025.acl-industry)

Challenge:	Recent work has shown large language models are adept at text generation and fine-tuning for downstream NLP tasks.
Approach:	They propose a system that generates paraphrased examples in autoregressive fashion using a neural network without the need for techniques such as top-k word selection or beam search.
Outcome:	The proposed system generates paraphrased examples in autoregressive fashion without the need for techniques such as top-k word selection or beam search.

Copied to clipboard

Yinghui Li, Shang Qin, Jingheng Ye, Haojing Huang, Yangning Li, Shu-Yu Guo, Libo Qin, Xuming Hu, Wenhao Jiang, Hai-Tao Zheng, Philip S. Yu

What Makes Sentences Semantically Related? A Textual Relatedness Dataset and Empirical Study (2023.eacl-main)

Challenge:	Recent studies have shown that Large Language Models’ performance as correctors on Chinese Grammatical Error Correction (CGEC) remains unsatisfactory due to the challenging nature of the task.
Approach:	They propose a training framework EXAM that uses LLMs as explainers to enhance CGEC small models and a novel evaluation method SEE that utilizes LLM as evaluators to bring more reasonable evaluations.
Outcome:	The proposed methods improve the performance of LLMs on Chinese Grammatical Error Correction (CGEC) task.

Copied to clipboard

Mohamed Abdalla, Krishnapriya Vishnubhotla, Saif Mohammad

Challenge:	Existing work on semantic relatedness has focused on semantic similarity because of a lack of relatedness datasets.
Approach:	They propose a dataset for semantic relatedness that has 5,500 English sentence pairs manually annotated using a comparative annotation framework.
Outcome:	The proposed dataset has 5,500 English sentence pairs manually annotated using a comparative annotation framework.

Quantifying Context Overlap for Training Word Embeddings (D18-1)

Copied to clipboard

Yimeng Zhuang, Jinghui Xie, Yinhe Zheng, Xuan Zhu

Parameter-free Sentence Embedding via Orthogonal Basis (D19-1)

Challenge:	Experimental results show that word embeddings can be improved using word embeds . word embedings are a popular form of natural language processing .
Approach:	They propose to estimate second order co-occurrence relations based on context overlap . they use the augmented data to enhance word embeddings learning .
Outcome:	The proposed model improves word vectors for word similarity and downstream NLP tasks.

Copied to clipboard

Ziyi Yang, Chenguang Zhu, Weizhu Chen

Cross-lingual and Cross-domain Transfer Learning for Automatic Term Extraction from Low Resource Data (2022.lrec-1)

Challenge:	Existing methods to build sentence embeddings are parameterized and require training to optimize their parameters.
Approach:	They propose a non-parameterized method to combine pre-trained word embeddings into sentence representations using an orthogonal basis of the word vector subspace and its surrounding context.
Outcome:	The proposed method shows superior performance on 11 downstream NLP tasks and is competitive to other methods relying on large amounts of labelled data or prolonged training time.

Copied to clipboard

Amir Hazem, Merieme Bouhandi, Florian Boudin, Beatrice Daille

A Survey in Automatic Irony Processing: Linguistic, Cognitive, and Multi-X Perspectives (2022.coling-1)

Challenge:	Automatic Term Extraction (ATE) is a key component for domain knowledge understanding and can be used for further NLP applications.
Approach:	They propose to fine-tune pre-trained BERT models for automatic Term Extraction (ATE) using cross-lingual and cross-domain transfer learning to extract single and multi-word terms.
Outcome:	The proposed models can capture cross-domain and cross-lingual terminologically-marked contexts shared by terms, opening a new design-pattern for ATE.

Copied to clipboard

Qingcheng Zeng, An-Ran Li

Sentiment Analysis

Challenge:	figurative language research has focused on sarcasm and irony, but there is still a gap in the field.
Approach:	They propose to review computational irony, cognitive science, and neural models of irony processing . they aim to encourage a balanced and equal research environment in figurative languages .
Outcome:	The proposed multi-X irony processing perspectives will provide an overview of computational irony, insights from linguisic theory and cognitive science, and interactions with downstream NLP tasks.

Robust Fragment-Based Framework for Cross-lingual Sentence Retrieval (2021.findings-emnlp)

Copied to clipboard

Nattapol Trijakwanich, Peerat Limkonchotiwat, Raheem Sarwar, Wannaphong Phatthiyaphaibun, Ekapol Chuangsuwanich, Sarana Nutanong

XferBench: a Data-Driven Benchmark for Emergent Language (2024.naacl-long)

Challenge:	Cross-lingual Sentence Retrieval (CLSR) aims at retrieving parallel sentence pairs that are translations of each other from a multilingual set of comparable documents.
Approach:	They propose a framework for cross-lingual sentence retrieval that uses a collection of fragments to improve sentence retrievals.
Outcome:	The proposed framework improves the retrieval robustness of the base sentences encoded by m-USE, LASER, and LaBSE.

Copied to clipboard

Brendon Boldt, David Mortensen

Challenge:	Existing methods to teach models to "language" are full of bias, toxicity, and potential intellectual property violations.
Approach:	They propose a benchmark for evaluating the overall quality of emergent languages using data-driven methods.
Outcome:	The proposed benchmark is based on utterances from the emergent language and is validated using human, synthetic, and emergentic language baselines.

ViLexNorm: A Lexical Normalization Corpus for Vietnamese Social Media Text (2024.eacl-long)

Copied to clipboard

Thanh-Nhi Nguyen, Thanh-Phong Le, Kiet Nguyen

Challenge:	Lexical normalization is a fundamental task in Natural Language Processing (NLP) it involves the transformation of words into their canonical forms.
Approach:	They present a corpus of Vietnamese words annotated by human annotators for the Vietnamese lexical normalization task.
Outcome:	The best-performing system achieved 57.74% using the Error Reduction Rate (ERR) metric with the Leave-As-Is (LAI) baseline.

Mini But Mighty: Efficient Multilingual Pretraining with Linguistically-Informed Data Selection (2023.findings-eacl)

Copied to clipboard

Tolulope Ogunremi, Dan Jurafsky, Christopher Manning

Crossing Domains without Labels: Distant Supervision for Term Extraction (2025.emnlp-industry)

Challenge:	AfriBERTa shows that training transformer models from scratch on 1GB of data from many unrelated African languages outperforms massively multilingual models on downstream NLP tasks.
Approach:	They propose that training on smaller amounts of data but from related languages could match the performance of models trained on large, unrelated data.
Outcome:	The proposed model outperforms models trained on large, unrelated datasets on downstream NLP tasks.

Copied to clipboard

Elena Senger, Yuri Campbell, Rob Van Der Goot, Barbara Plank

Why Aren’t We NER Yet? Artifacts of ASR Errors in Named Entity Recognition in Spontaneous Speech Transcripts (2023.acl-long)

Challenge:	Current state-of-the-art methods require expensive human annotation and struggle with domain transfer, limiting their practical deployment.
Approach:	They propose a benchmark spanning seven diverse domains to evaluate ATE performance . they propose psuedo-labels and post-hoc heuristics to ensure generalizability .
Outcome:	The proposed model outperforms supervised cross-domain encoder models and few-shot learning baselines on the document- and corpus-levels and its GPT-4o teacher on the benchmark.

Copied to clipboard

Piotr Szymański, Lukasz Augustyniak, Mikolaj Morzy, Adrian Szymczak, Krzysztof Surdyk, Piotr Żelasko

Speech & Audio in NLP

Challenge:	despite advances in language models, the transcript of spontaneous human-human conversations remains an insurmountable challenge for most models.
Approach:	They examine the relationship between ASR and NER errors which limit NER models' ability to recover entity mentions from spontaneous speech transcripts.
Outcome:	The proposed model fails even if no word errors are introduced by the ASR . the proposed model's performance deteriorates when applied to the ASL outputs .

A Cautious Generalization Goes a Long Way: Learning Morphophonological Rules (2023.acl-long)

Copied to clipboard

Salam Khalifa, Sarah Payne, Jordan Kodner, Ellen Broselow, Owen Rambow

Challenge:	Explicit linguistic knowledge encoded by rule-based morphological analyzers is expensive and non-trivial . creating such resources is tedious and requires additional efforts to extract human-interpretable patterns from them.
Approach:	They propose a method for automatically learning morphophonological rules of Arabic from a corpus.
Outcome:	The proposed approach produces a set of generalizable rules from a dataset.

Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text Summarization (2021.naacl-main)

Copied to clipboard

Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Lorraine Li, Pavan Kapanipathi, Kartik Talamadupula

Reasoning

Challenge:	Large-scale, open Natural Language Inference datasets have catalyzed the development of NLI models that exhibit close to human-level performance, but the use of these models for other downstream NLP tasks has met with limited success.
Approach:	They use multiple-choice reading comprehension and checking factual correctness of textual summarization tasks to investigate potential reasons for this . authors leverage abundance of data from reading comprehension datasets into longer-premise NLI datasets to improve their models .
Outcome:	The proposed models outperform models trained on converted datasets due to the difference in premise lengths.

Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token (2022.findings-emnlp)

Copied to clipboard

Baohao Liao, David Thulke, Sanjika Hewavitharana, Hermann Ney, Christof Monz

BERTrade: Using Contextual Embeddings to Parse Old French (2022.lrec-1)

Challenge:	Large-scale pre-trained MLMs can be used to generalize well to a wide range of tasks.
Approach:	They propose to append [MASK]s at a later layer to reduce sequence length for earlier layers.
Outcome:	The proposed method outperforms RoBERTa for 6 out of 8 GLUE tasks on average by 0.4%.

Copied to clipboard

Loïc Grobol, Mathilde Regnault, Pedro Ortiz Suarez, Benoît Sagot, Laurent Romary, Benoit Crabbé

Sorting through the noise: Testing robustness of information processing in pre-trained language models (2021.emnlp-main)

Challenge:	a growing interest in digital humanities for automatic processing and annotation of historical texts is generating new models for historical languages.
Approach:	They use POS-tagging and dependency parsing to evaluate contextual word embedding models . Old French is one of the historical languages for which they have the largest amount of syntactically annotated data .
Outcome:	The proposed model can be used to improve performance in Old French, the authors show . they use POS-tagging and dependency parsing to evaluate the model's quality .

Copied to clipboard

Lalchand Pandia, Allyson Ettinger

Robustness in NLP

Challenge:	Pre-trained language models have shown impressive performance on downstream NLP tasks, but we have yet to establish a clear understanding of their sophistication when it comes to processing, retaining, and applying information presented in their input.
Approach:	They examine how robustly pre-trained LMs retain and apply relevant context information in the face of distracting content.
Outcome:	The proposed models retain and use critical context information in the face of distracting content, while models are susceptible to factors of semantic similarity and word position.

Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages (2020.coling-main)

Copied to clipboard

Diptesh Kanojia, Raj Dabre, Shubham Dewangan, Pushpak Bhattacharyya, Gholamreza Haffari, Malhar Kulkarni

Evaluating and Mitigating Inherent Linguistic Bias of African American English through Inference (2022.coling-1)

Challenge:	a study of 14 Indian languages shows that cognates can be detected by word embeddings . cognates are variants of the same lexical form across languages .
Approach:	They propose to use cross-lingual word embeddings to detect cognates among 14 Indian languages . they then evaluate the impact of their method on neural machine translation .
Outcome:	The proposed method improves on a dataset of 12 Indian languages . it also improves quality of the extracted cognates by up to 2.76 BLEU .

Copied to clipboard

Jamell Dacon, Haochen Liu, Jiliang Tang

Global Textual Relation Embedding for Relational Understanding (P19-1)

Challenge:	Recent studies show that NLP models trained on standard English produce biased outcomes against underrepresented English varieties.
Approach:	They propose a morphosyntactically-informed rule-based translation method that uses a greedy algorithm to debiase NLP models.
Outcome:	The proposed framework outperforms large language models while maintaining or improving the prediction performance.

Copied to clipboard

Zhiyu Chen, Hanwen Zha, Honglei Liu, Wenhu Chen, Xifeng Yan, Yu Su

Synthesizing Human Gaze Feedback for Improved NLP Performance (2023.eacl-main)

Challenge:	Existing methods to learn textual relation embeddings are lacking in large open-domain corpora.
Approach:	They propose to learn a general-purpose embedding of textual relations using a large dataset from Freebase.
Outcome:	The proposed embedding can facilitate downstream tasks requiring relational understanding of the text.

Copied to clipboard

Varun Khurana, Yaman Kumar, Nora Hollenstein, Rajesh Kumar, Balaji Krishnamurthy

Challenge:	Prior work on eye tracking and NLP reveals that human scanpaths can aid in understanding and performance of NLP models.
Approach:	They propose a model for generating human scanpaths over text that approximates meaningful cognitive signals in human gaze patterns.
Outcome:	The proposed model can approximate meaningful cognitive signals in human gaze patterns.

On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation (2021.acl-long)

Copied to clipboard

Ruidan He, Linlin Liu, Hai Ye, Qingyu Tan, Bosheng Ding, Liying Cheng, Jiawei Low, Lidong Bing, Luo Si

Universal Proposition Bank 2.0 (2022.lrec-1)

Challenge:	Existing studies have shown that adapter-based tuning is more parameter-efficient than fine-tuning.
Approach:	They propose to add adapter modules to a pretrained language model and update the parameters of adapter module when learning on a downstream task.
Outcome:	The proposed method outperforms fine-tuning on low-resource and cross-lingual tasks and settings.

Copied to clipboard

Ishan Jindal, Alexandre Rademaker, Michał Ulewicz, Ha Linh, Huyen Nguyen, Khoi-Nguyen Tran, Huaiyu Zhu, Yunyao Li

Syntactic Text Processing

Challenge:	Semantic role labeling (SRL) is a shallow semantic parsing task that identifies "who did what to whom when, where etc." SRL is useful in a wide range of downstream NLP tasks and real-world applications.
Approach:	They propose a method to generate shallow semantic parsing tasks using monolingual SRL and multilingual parallel data.
Outcome:	The proposed method improves the quality of the generated propbanks.

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models (2022.emnlp-main)

Copied to clipboard

Lan Jiang, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Rui Jiang

Robustness in NLP

Challenge:	Recent studies have highlighted the lack of adversarial robustness in pre-trained models.
Approach:	They propose a fine-tuning approach that conducts selective updates when adapting pre-trained models to downstream tasks.
Outcome:	The proposed approach improves adversarial robustness on downstream tasks . it eliminates spurious updates, leading to flatter and wider optima than the conventional method .

MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices (2020.acl-main)

Copied to clipboard

Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, Denny Zhou

Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings (2025.acl-long)

Challenge:	Empirical studies show that MobileBERT is 4.3x smaller and 5.5x faster than BERT_BASE . BERT is one of the largest models ever in NLP, but suffers from heavy model size and high latency .
Approach:	They propose a tool to compress and accelerate the popular BERT model by task-agnostic application.
Outcome:	The proposed model is 4.3x smaller and 5.5x faster than BERT_BASE . it achieves competitive results on well-known benchmarks .

Copied to clipboard

Chenghao Sun, Zhen Huang, Yonggang Zhang, Le Lu, Houqiang Li, Xinmei Tian, Xu Shen, Jieping Ye

ADePT: Auto-encoder based Differentially Private Text Transformation (2021.eacl-main)

Challenge:	Large language models excel at downstream NLP tasks through in-context learning . however, the internal mechanisms behind ICL remain under-explored .
Approach:	They propose a PC patching approach to identify modules where input-label mappings function . they observe and verify that key heads utilize input-labeled mappings to generate target labels for new queries.
Outcome:	The proposed approach detects modules where input-label mappings function . it also detects that key heads use the mappings to generate labels for new queries .

Copied to clipboard

Satyapriya Krishna, Rahul Gupta, Christophe Dupuy

Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations (2021.eacl-main)

Challenge:	Differential privacy is an important privacy concern when building statistical models on data containing sensitive information.
Approach:	They propose a utility-preserving differentially private text transformation algorithm using auto-encoders that can be used to transform text to offer robustness against attacks and produce transformations with high semantic quality.
Outcome:	The proposed model performs better against membership inference attacks while offering lower to no degradation in the utility of the underlying transformation process compared to baselines.

Copied to clipboard

Pieter Fivez, Simon Suster, Walter Daelemans

Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization (2020.findings-emnlp)

Challenge:	Existing approaches to encoding biomedical names require lexical and domain-specific semantics to be robust.
Approach:	They propose a method which encodes biomedical names with lexical and domain-specific semantics . they use conceptual grounding constraints to align encoded names to pretrained embeddings of their concept identifiers a technique that is effective even when using a deep averaging network .
Outcome:	The proposed representations capture more domain-specific semantics while remaining universally applicable across biomedical corpora and domains.

Copied to clipboard

Kunal Chawla, Diyi Yang

Subword-level Word Vector Representations for Korean (P18-1)

Challenge:	Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences.
Approach:	They propose a semi-supervised formality style transfer model that utilizes a language model-based discriminator to maximize the likelihood of the output sentence being formal.
Outcome:	The proposed model outperforms state-of-the-art models in terms of automated metrics and human judgement.

Copied to clipboard

Sungjoon Park, Jeongmin Byun, Sion Baek, Yongseok Cho, Alice Oh

CycleOIE: A Low-Resource Training Framework For Open Information Extraction (2025.coling-main)

Challenge:	Existing research on word vectors for English focuses on decomposing words into subword units and using subwords to improve performance.
Approach:	They propose to decompose Korean words into the jamo-level, beyond the character-level . they develop Korean test sets for word similarity and analogy and make them publicly available .
Outcome:	The proposed method outperforms word2vec and character-level skip-grams on similarity and analogy tasks and contributes positively toward downstream NLP tasks such as sentiment analysis.

Copied to clipboard

Zhihong Jin, Chunhong Zhang, Zheng Hu, Jibin Yu, Ruiqi Ma, Qingyun Chen, Xiaohao Liao, Yanxing Zhang

WEXEA: Wikipedia EXhaustive Entity Annotation (2020.lrec-1)

Challenge:	Open Information Extraction (OpenIE) models rely heavily on large amounts of annotated data.
Approach:	They propose a training framework that maximizes data efficiency through a cycle-consistency mechanism.
Outcome:	The proposed approach improves the quality of training data by curating low-quality datasets annotated by a large language model.

Copied to clipboard

Michael Strobl, Amine Trabelsi, Osmar Zaiane

Language Models as Knowledge Bases? (D19-1)

Challenge:	Existing methods for extracting factual knowledge from text are limited to a few subtasks.
Approach:	They propose to use Wikipedia to build a corpus with exhaustive annotations of entity mentions.
Outcome:	The proposed system can be used to build supervised datasets and can be reproduced by everyone.

Copied to clipboard

Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, Alexander Miller

PrAd: Prompt Adaptive Tuning for Decoder-only Language Models (2025.findings-emnlp)

Challenge:	Recent advances in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks.
Approach:	They present a method for pretraining language models on large textual corpora . they find that they can store relational knowledge and answer queries structured as "fill-in-the-blank" queries.
Outcome:	The proposed language models can recall factual knowledge without fine-tuning without fine tuning . the proposed models can answer queries structured as "fill-in-the-blank" cloze statements .

Copied to clipboard

Youneng Ma, Junyi He, Haojun Fei

Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation (2021.acl-long)

Challenge:	Prompt-based methods suffer from increased input lengths and sensitivity to weight initialization . adapter-based approaches can substantially increase inference time .
Approach:	a new paradigm for prompt-based tuning addresses the problem of fine tuning pretrained models . prompt--based methods suffer from increased input lengths and sensitivity to weight initialization . a prompt-oriented approach employs adapters for flexible input transformation .
Outcome:	a proposed framework can achieve comparable or better performance and higher inference efficiency even in multi-task scenarios.

Copied to clipboard

Shizhe Diao, Ruijia Xu, Hongjin Su, Yilei Jiang, Yan Song, Tong Zhang

Multi-step Jailbreaking Privacy Attacks on ChatGPT (2023.findings-emnlp)

Challenge:	Existing methods to train pre-trained models require domain-specific data and computational resources.
Approach:	They propose a domain-aware N-gram Adaptor to incorporate unseen and domain-specific words into a generic pretrained model.
Outcome:	The proposed model can improve on eight low-resource tasks using limited data with lower computational costs.

Copied to clipboard

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, Yangqiu Song

Definition Frames: Using Definitions for Hybrid Concept Representations (2020.coling-main)

Challenge:	With the rapid evolution of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts.
Approach:	They propose to integrate ChatGPT and Bing GPT3 into their applications to create a set of LLMs that can be used to generate NLP tasks with appropriate prompts.
Outcome:	The proposed models can be zero-shot or few-shot learners to solve specified tasks and can even be zero or few shot learners.

Copied to clipboard

Evangelia Spiliopoulou, Artidoro Pagnoni, Eduard Hovy

Explainability & Interpretability in NLP

Challenge:	a new hybrid representation is proposed that encodes semantic information extracted from definitions.
Approach:	They propose a matrix distributed representation extracted from definitions where each dimension is semantically interpretable.
Outcome:	The proposed representations have competitive performance with other distributional semantic approaches on word similarity tasks.

On Utilizing Constituent Language Resources to Improve Downstream Tasks in Hinglish (2022.findings-emnlp)

Copied to clipboard

Vishwajeet Kumar, Rudra Murthy, Tejas Dhamecha

Cognition-aware Cognate Detection (2021.eacl-main)

Challenge:	Intuitively, Hindi and English corpora should aid improve task performance on code-switched Hindi-English.
Approach:	They propose a meta-learning framework that utilizes the labelled resources of the downstream tasks in the constituent languages to improve task performance.
Outcome:	The proposed framework improves the performance on downstream tasks on code-switched Hindi-English.

Copied to clipboard

Diptesh Kanojia, Prashant Sharma, Sayali Ghodekar, Pushpak Bhattacharyya, Gholamreza Haffari, Malhar Kulkarni

Disfluency Correction using Unsupervised and Semi-supervised Learning (2021.eacl-main)

Challenge:	Existing approaches to cognate detection use orthographic, phonetic and semantic similarity based features sets.
Approach:	They propose a method for enriching feature sets with cognitive features extracted from gaze behaviour data from human readers’ gaze behaviour.
Outcome:	The proposed method improves cognate detection performance by 10% and 12% over existing methods.

Copied to clipboard

Nikhil Saini, Drumil Trivedi, Shreya Khare, Tejas Dhamecha, Preethi Jyothi, Samarth Bharadwaj, Pushpak Bhattacharyya

Low-Resource NLP

Challenge:	Disfluencies in conversational speech can affect performance of downstream NLP tasks.
Approach:	They propose a disfluency correction model that converts disfluent to fluent text . they use unsupervised encoder-decoder models to generate semi-supervised models .
Outcome:	The proposed model achieves a BLEU score of 79.39 on the Switchboard corpus test set and 85.28 with semi-supervision.

LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content (2025.findings-naacl)

Copied to clipboard

Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Maram Hasanain, Sahinur Rahman Laskar, Naeemul Hassan, Firoj Alam

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

Challenge:	Large Language Models (LLMs) have demonstrated remarkable success as general-purpose task solvers across various fields.
Approach:	They propose to develop a specialized LLM for analyzing news and social media content in a multilingual context.
Outcome:	The proposed model outperforms the current state-of-the-art on 23 testing sets and achieves comparable performance on 8 sets.

Copied to clipboard

Kaiyu Huang, Degen Huang, Zhuang Liu, Fengran Mo

Syntactic Text Processing

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

PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models (2024.naacl-long)

Copied to clipboard

HyunJin Kim, Young Jin Kim, JinYeong Bak

Context Analysis for Pre-trained Masked Language Models (2020.findings-emnlp)

Challenge:	Pre-trained language models (PLMs) show impressive performance in various downstream NLP tasks.
Approach:	They propose a Parameter-Efficient Fine-Tuning method that integrates with context representations from test data to perform downstream tasks.
Outcome:	The proposed method outperforms other methods in memory and latency efficiency and maintains sentence meaning and generating appropriate language and styles.

Copied to clipboard

Yi-An Lai, Garima Lalwani, Yi Zhang

Large Product Key Memory for Pretrained Language Models (2020.findings-emnlp)

Challenge:	Pre-trained language models that learn contextualized word representations from a large un-annotated corpus have become a standard component for many downstream NLP tasks.
Approach:	They propose to use a masking and gradient approach to evaluate the impact of context on the word representation.
Outcome:	The proposed model architectures are architecture agnostic and gradient based.

Copied to clipboard

Gyuwan Kim, Tae Hwan Jung

Recent advances in neural metaphor processing: A linguistic, cognitive and social perspective (2021.naacl-main)

Challenge:	Existing product key memory (PKM) models that increase model capacity with insignificant computational overhead are limited to causal language modeling.
Approach:	They propose product key memory (PKM) that enables very efficient and exact nearest neighbor search in a large number of learnable memory slots.
Outcome:	The proposed product key memory improves model capacity and performance by replacing a feed-forward network with a model weighted model.

Copied to clipboard

Xiaoyu Tong, Ekaterina Shutova, Martha Lewis

Cognitive Modeling

Challenge:	Metaphor processing systems have benefited from recent studies on the role of metaphor in communication and deep learning for natural language processing.
Approach:	They present a review of automated metaphor processing and discuss their results from downstream NLP tasks.
Outcome:	The proposed system is based on the findings of a systematic and comprehensive survey of metaphor processing systems published five years ago.

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

Copied to clipboard

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

Syntactic Text Processing

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

Cross-lingual Contextualized Phrase Retrieval (2024.findings-emnlp)

Copied to clipboard

Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe

Zero-shot Disfluency Detection for Indian Languages (2022.coling-1)

Challenge:	Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks.
Approach:	They propose a task formulation of dense retrieval, cross-lingual contextualized phrase retrieval . they extract pairs of cross-linguistic phrases using word alignment information .
Outcome:	The proposed task formulation surpasses baselines on the phrase retrieval task and a downstream task, i.e., machine translation, and achieves top-1 accuracy 13 points higher.

Copied to clipboard

Rohit Kundu, Preethi Jyothi, Pushpak Bhattacharyya

Token and Head Adaptive Transformers for Efficient Natural Language Processing (2022.coling-1)

Challenge:	Disfluency correction models can help alleviate this problem, but the unavailability of labeled data in low-resource languages impairs progress.
Approach:	They propose to use a pretrained multilingual model to detect zero-shot disfluency in Indian languages.
Outcome:	The proposed model achieves F1 scores of 75 and higher on five disfluency types across four languages.

Copied to clipboard

Chonghan Lee, Md Fahim Faysal Khan, Rita Brugarolas Brufau, Ke Ding, Vijaykrishnan Narayanan

Sinhala Encoder-only Language Models and Evaluation (2025.acl-long)

Challenge:	Pre-trained language models like BERT have shown significant accuracy improvements on various tasks, but their computational cost and memory footprint are prohibitive.
Approach:	They propose to extend Length Adaptive Transformer to extend the model to a token and head pruning scheme to optimize pruning efficiency.
Outcome:	The proposed model can compress and accelerate BERT-based models by fine-tuning and a token and head pruning scheme.

Copied to clipboard

Tharindu Ranasinghe, Hansi Hettiarachchi, Nadeesha Chathurangi Naradde Vidana Pathirana, Damith Premasiri, Lasitha Uyangodage, Isuri Nanomi Arachchige, Alistair Plum, Paul Rayson, Ruslan Mitkov

How transfer learning impacts linguistic knowledge in deep NLP models? (2021.findings-acl)

Challenge:	Recent advances in language models (LMs) have produced excellent results in many NLP tasks, but their effectiveness is highly dependent on available pre-training resources.
Approach:	They propose to collect the largest monolingual corpus for Sinhala and compile a benchmark and evaluate LMs on it.
Outcome:	The proposed language models outperform the popular multilingual LMs in downstream NLP tasks.

Copied to clipboard

Nadir Durrani, Hassan Sajjad, Fahim Dalvi

TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference (2021.naacl-main)

Challenge:	Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured at different layers of the model.
Approach:	They propose to fine-tune pre-trained models towards downstream NLP tasks to capture linguistic knowledge.
Outcome:	The proposed model is adapted to GLUE tasks and retains linguistic information in the network while forgetting it.

Copied to clipboard

Deming Ye, Yankai Lin, Yufei Huang, Maosong Sun

Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction (2020.lrec-1)

Challenge:	Existing pre-trained language models (PLMs) are expensive in inference, making them impractical in resource-limited real-world applications.
Approach:	They propose a dynamic token reduction approach to accelerate PLMs' inference by adapting the layer number of each token to avoid redundant calculation.
Outcome:	The proposed approach speeds up BERT by 2-5 times and improves performance in long-text tasks with less computation.

Copied to clipboard

Danushka Bollegala, Ryuichi Kiryo, Kosuke Tsujino, Haruki Yukawa

Learning to Selectively Learn for Weakly-supervised Paraphrase Generation (2021.emnlp-main)

Challenge:	Language-independent tokenisation (LIT) methods that do not require labelled language resources or lexicons have gained popularity because of their compactness and ability to handle unseen or rare words.
Approach:	They empirically compare language-independent tokenisation methods with language-specific tokenisation (LST) methods using carefully created lexicons and training resources.
Outcome:	The proposed methods outperform LIT and LST on evaluation tasks across eight languages.

Copied to clipboard

Kaize Ding, Dingcheng Li, Alexander Hanbo Li, Xing Fan, Chenlei Guo, Yang Liu, Huan Liu

Text Generation

Challenge:	Existing approaches to generate paraphrases with weak supervision are limited in real-world scenarios due to the lack of coherent and controllable generated paraphrase.
Approach:	They propose a method to generate high-quality paraphrases with weak supervision . they obtain abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion .
Outcome:	The proposed approach achieves significant improvements over existing methods and is even comparable in performance with supervised state-of-the-arts.

IntKB: A Verifiable Interactive Framework for Knowledge Base Completion (2020.coling-main)

Copied to clipboard

Bernhard Kratzwald, Guo Kunpeng, Stefan Feuerriegel, Dennis Diefenbach

Knowledge Representation

Challenge:	Knowledge bases (KBs) present databases that store information about entities and relations among them.
Approach:	They propose a question-based interactive framework for KB completion from text . their framework generates facts that are aligned with text snippets and is immediately verifiable by humans .
Outcome:	The proposed framework achieves a hit@1 ratio of 29.7% for initial unseen relations, and gradually improves to 46.2%.

StructuralLM: Structural Pre-training for Form Understanding (2021.acl-long)

Copied to clipboard

Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

EFTNAS: Searching for Efficient Language Models in First-Order Weight-Reordered Super-Networks (2024.lrec-main)

Challenge:	Existing pre-trained language models focus on text-only representation, neglecting cell-level layout information.
Approach:	They propose a pre-training approach to leverage cell and layout information from scanned documents.
Outcome:	The proposed model achieves state-of-the-art in various downstream tasks . it uses 2Dposition embeddings to model word-level layout information .

Copied to clipboard

Juan Pablo Munoz, Yi Zheng, Nilesh Jain

Video-Grounded Dialogues with Pretrained Generation Language Models (2020.acl-main)

Challenge:	Depending on the size of transformer-based models, they can be restricted from deployment in resource-constrained environments.
Approach:	They propose to combine neural architecture search and network pruning techniques to generate and train weight-sharing super-networks that contain efficient transformer-based models.
Outcome:	The proposed model achieves high-performing, high-performance subnetworks on the general language understanding evaluation and the Stanford Question Answering Dataset.

Copied to clipboard

Hung Le, Steven C.H. Hoi

Natural Language Interfaces

Challenge:	Pre-trained language models have shown success in improving downstream NLP tasks . pre-tuned models capture textual dependencies in text data of rich semantics .
Approach:	They propose a framework for improving video-grounded dialogue by extending GPT-2 models . they propose to combine visual and textual representation into a structured sequence .
Outcome:	The proposed framework improves audio-visual scene-aware dialogues benchmark on AVSD . it is based on a large pre-trained GPT-2 network and can generate natural responses .

Reverse-Engineering the Reader (2024.emnlp-main)

Copied to clipboard

Samuel Kiegeland, Ethan Wilcox, Afra Amini, David Reich, Ryan Cotterell

LuxemBERT: Simple and Practical Data Augmentation in Language Model Pre-Training for Luxembourgish (2022.lrec-1)

Challenge:	Existing studies have sought to determine to what extent language models can serve as useful models of human cognition by aligning them to human psychometric data.
Approach:	They propose a method to fine-tune a language model to implicitly optimize parameters of a linear regressor that directly predicts humans’ reading times of in-context linguistic units.
Outcome:	The proposed technique improves language models’ psychometric predictive power but also its perplexity on held-out test data.

Copied to clipboard

Cedric Lothritz, Bertrand Lebichot, Kevin Allix, Lisa Veiber, Tegawende Bissyande, Jacques Klein, Andrey Boytsov, Clément Lefebvre, Anne Goujon

EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation (2024.lrec-main)

Challenge:	Pre-trained Language Models such as BERT are ubiquitous in NLP but are scarce for low-resource languages such as Luxembourgish.
Approach:	They propose a BERT model for Luxembourgish language that they use to augment pre-training datasets by partially translating text data from a closely related language.
Outcome:	The proposed model outperforms the baseline model and the mBERT model in Luxembourgish.

Copied to clipboard

Atnafu Lambebo Tonja, Israel Abebe Azime, Tadesse Destaw Belay, Mesay Gemeda Yigezu, Moges Ahmed Ah Mehamed, Abinew Ali Ayele, Ebrahim Chekol Jibril, Michael Melese Woldeyohannis, Olga Kolesnikova, Philipp Slusallek, Dietrich Klakow, Seid Muhie Yimam

Coreferential Reasoning Learning for Language Representation (2020.emnlp-main)

Challenge:	Low-resource languages are lagging behind current state-of-the-art (SOTA) developments in the field of NLP due to insufficient resources to train LLMs.
Approach:	They propose to use multilingual large language models for five Ethiopian languages and a benchmark dataset to evaluate their performance.
Outcome:	The proposed models outperform existing models in five Ethiopian languages and a benchmark dataset for various downstream NLP tasks.

Copied to clipboard

Deming Ye, Yankai Lin, Jiaju Du, Zhenghao Liu, Peng Li, Maosong Sun, Zhiyuan Liu

Split or Merge: Which is Better for Unsupervised RST Parsing? (D19-1)

Challenge:	Existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse.
Approach:	They propose a language representation model that captures coreferential relations in context.
Outcome:	The proposed model can achieve significant improvements on downstream NLP tasks while maintaining comparable performance to baseline models on other common NLP task.

Copied to clipboard

Naoki Kobayashi, Tsutomu Hirao, Kengo Nakamura, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata

Give your Text Representation Models some Love: the Case for Basque (2020.lrec-1)

Challenge:	Rhetorical Structure Theory (RST) parsers have been based on supervised learning approaches that require an annotated corpus of sufficient size and quality.
Approach:	They propose two unsupervised methods that build an optimal RST tree based on a dissimilarity score function for splitting a text span into smaller ones and a similarity score for merging two adjacent spans into a large one.
Outcome:	The proposed method achieves the best score on English and German RST treebanks, around 0.8 F1 score, close to the previous supervised parsers.

Copied to clipboard

Rodrigo Agerri, Iñaki San Vicente, Jon Ander Campos, Ander Barrena, Xabier Saralegi, Aitor Soroa, Eneko Agirre

Plug-and-Play Knowledge Injection for Pre-trained Language Models (2023.acl-long)

Challenge:	Word embeddings and pre-trained language models are expensive to train and are often used by small companies and research groups to build their own.
Approach:	They propose to use word embeddings and pre-trained language models to build rich representations of text and improve NLP tasks.
Outcome:	The proposed models perform better than publicly available versions in downstream NLP tasks for Basque.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Pre-Training BERT on Domain Resources for Short Answer Grading (D19-1)

Challenge:	Existing knowledge injection methods are not suitable for enhancing pre-trained language models with external knowledge bases.
Approach:	They propose a plug-and-play knowledge injection method where knowledge bases are injected into frozen existing downstream models by a knowledge plugin.
Outcome:	The proposed method improves the performance of knowledge injection on knowledge-driven tasks while keeping model parameters frozen.

Copied to clipboard

Chul Sung, Tejas Dhamecha, Swarnadeep Saha, Tengfei Ma, Vinay Reddy, Rishi Arora

Improve Dense Passage Retrieval with Entailment Tuning (2024.emnlp-main)

Challenge:	Pre-trained contextualized representations have achieved state-of-the-art results on multiple downstream NLP tasks by fine-tuning with task-specific data.
Approach:	They propose to augment domain-specific data by using labeled short answering grading data for further enhancement of the pre-trained language model.
Outcome:	The proposed model can be enhanced by augmenting data from domain-specific resources like textbooks and labeled short answering grading data.

Copied to clipboard

Lu Dai, Hao Liu, Hui Xiong

Information Retrieval

Challenge:	Existing methods for dense retrieval have demonstrated remarkable performance in IR tasks.
Approach:	They propose a method to improve the embedding of dense retrievers by using existence claim as a bridge.
Outcome:	The proposed method can be plugged into current dense retrieval methods and the results are published in the journal Nature.

Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start (2020.emnlp-main)

Copied to clipboard

Wenpeng Yin, Nazneen Fatema Rajani, Dragomir Radev, Richard Socher, Caiming Xiong

Choose Your Transformer: Improved Transferability Estimation of Transformer Models on Classification Tasks (2024.findings-acl)

Challenge:	a current approach to solving NLP problems is to build a problem-specific dataset . current approaches do not allow for transforming tasks into textual entailment .
Approach:	They propose a pretrained textual entailment system that can generalize across domains . they argue that when is it worth transforming an NLP task into textual detailment?
Outcome:	The proposed model can generalize across domains with few examples, the authors argue . they show that it can be used for several downstream NLP tasks with limited annotations .

Copied to clipboard

Lukas Garbaciauskas, Max Ploner, Alan Akbik

Rethinking the Evaluation of In-Context Learning for LLMs (2024.emnlp-main)

Challenge:	Existing models for NLP tasks require fine-tuning, but it is computationally infeasible.
Approach:	They propose an approach that inexpensively estimates a ranking of the expected performance of a given set of transformer language models for a specific task.
Outcome:	The proposed model improves the Pearson correlation coefficient between the true model ranks and the estimate.

Copied to clipboard

Guoxin Yu, Lemao Liu, Mo Yu, Yue Yu, Xiang Ao

Injecting Domain Knowledge in Language Models for Task-oriented Dialogue Systems (2022.emnlp-main)

Challenge:	Existing studies evaluate In-context learning methods based on task performance . however, this evaluation protocol overlooks the significant cost associated with the demonstration configuration process .
Approach:	They propose a two-dimensional evaluation paradigm that considers both configuration costs and task performance.
Outcome:	The proposed evaluation paradigm can be applied to any ICL method as a plugin.

Copied to clipboard

Denis Emelin, Daniele Bonadiman, Sawsan Alqahtani, Yi Zhang, Saab Mansour

What is in a name? Mitigating Name Bias in Text Embedding Similarity via Anonymization (2025.findings-acl)

Challenge:	Pre-trained language models lack domain-specific knowledge that does not naturally occur in pre-training data.
Approach:	They propose to inject domain-specific knowledge prior to fine-tuning on TOD tasks by using adapters that can be easily integrated with PLMs.
Outcome:	The proposed methods show that they can inject domain-specific knowledge prior to fine-tuning on TOD tasks.

Copied to clipboard

Sahil Manchanda, Pannaga Shivaswamy

Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding (2023.emnlp-main)

Challenge:	Text-embedding models often exhibit name bias due to data on which they are trained.
Approach:	They propose a method to mitigate name bias in text-embedding models by removing references to names from the text.
Outcome:	The proposed approach achieves significant performance gains on three downstream NLP tasks involving embedding similarities.

Copied to clipboard

Taolin Zhang, Ruyao Xu, Chengyu Wang, Zhongjie Duan, Cen Chen, Minghui Qiu, Dawei Cheng, Xiaofeng He, Weining Qian

Improving Input-label Mapping with Demonstration Replay for In-context Learning (2023.findings-emnlp)

Challenge:	Existing methods for pre-training KEPLMs with relational triples are difficult to adapt to close domains due to the lack of sufficient domain graph semantics.
Approach:	They propose a Knowledge-enhanced language representation learning framework for various closed domains that captures the implicit graph structure among the entities.
Outcome:	The proposed framework outperforms existing methods for pre-training KEPLMs in closed domains significantly.

Copied to clipboard

Zhuocheng Gong, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan

DPED: Multi-Layer Noise Distillation for Privacy-Preserving Text Embeddings (2025.emnlp-main)

Challenge:	In-context learning (ICL) is an emerging capability of large autoregressive language models where a few demonstrations are appended to the input to enhance the model’s understanding of downstream NLP tasks without directly adjusting the model parameters.
Approach:	They propose a method where a few demonstrations are appended to the input to enhance the model's understanding of downstream NLP tasks without directly adjusting the model parameters.
Outcome:	The proposed method significantly improves the input-label mapping in ICL demonstrations.

Copied to clipboard

Shuya Feng, Yuan Hong

Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models (2025.findings-emnlp)

Challenge:	Existing methods to train text embedding models under differential privacy constraints are difficult due to high dimensionality of language data and the presence of rare, identifying linguistic features.
Approach:	They propose a framework that leverages teacher-student distillation with noise injection to learn high-quality embeddings while providing differential privacy guarantees.
Outcome:	The proposed framework outperforms standard differentially private training methods on benchmark datasets and provides higher privacy-utility trade-offs.

Copied to clipboard

Ting Cai, Stephen Sheen, AnHai Doan

Multimodality

Challenge:	Existing solutions to expand table names are limited by the abbreviated column names of tables.
Approach:	They propose to use abbreviated tables to expand column names . they propose to introduce four new datasets with real-world abbrevations .
Outcome:	The proposed solution outperforms NameGuess in terms of accuracy and consistency over five datasets.

Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks (2025.acl-long)

Copied to clipboard

Ori Shapira, Shlomo Chazan, Amir David Nissan Cohen

Multimodality

Challenge:	a growing number of recorded human speech is recorded for automated processing, resulting in errors in the transcripts . a configurable framework is proposed to analyze transcript noise impact across noise levels and transcript-cleaning techniques.
Approach:	They propose a configurable framework for assessing task models in diverse noisy settings . framework facilitates investigation of task model behavior, which can support effective SLU solutions.
Outcome:	The proposed framework can analyze model behavior in various noise levels and transcript-cleaning techniques.

Small Data, Big Noise: Adversarial Training for Robust ParameterEfficient Fine-Tuning (2026.findings-acl)

Copied to clipboard

Eitan Cohen, Idan Simai, Uri Shaham