ACL 2023

2,788 papers

Top Research Directions

Research directions most represented by ACL 2023 papers.

Pre-Training Language Models on Specialized Corpora 60
Zero-Shot Cross-Lingual Transfer in Multilingual Language Models 55
Mitigating Data Scarcity in Low Resource Language Processing 42
Understanding Prompt Sensitivity in Language Models 36
Replacing Abstract Labels with Natural Language Descriptions 33
The Language Bias of English Centric Benchmarks 33
The Performance Advantage of Localized Language Pretraining 32
Factual Inaccuracy and Hallucination in Large Language Models 30
Shared Representation Learning via Simultaneous Multi-Task Training 29
Mitigating Cascading Errors in Sequential Processing Pipelines 28
Joint Multilingual Training for Cross-Lingual Transfer 28
The Fluency Control Tradeoff in Language Model Steering 27
Factual Consistency in Abstractive Summarization 27
The Mechanics of Bias Amplification in Language Models 27
Task Activation via In Context Demonstrations 26

Top Authors

AuthorPapers
Min Zhang20
Dongyan Zhao19
Xuanjing Huang19
Zhiyuan Liu18
Fei Huang17
Heng Ji17
Lidong Bing17
Maosong Sun17
Xipeng Qiu17
Yue Zhang16
Minlie Huang15
Zhou Zhao15
Kai-Wei Chang14
Yejin Choi14
Jie Zhou13
Nanyun Peng12
Shafiq Joty12
William Yang Wang12
Xiang Ren12
Dan Roth11

Impactful Papers

Papers from ACL 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
This prompt is measuring <mask>: evaluating bias evaluation in language models
This prompt is measuring \textlessmask\textgreater: evaluating bias evaluation in language models
TimelineQA: A Benchmark for Question Answering over Timelines
tmn at SemEval-2023 Task 9: Multilingual Tweet Intimacy Detection Using XLM-T, Google Translate, and Ensemble Learning
T.M. Scanlon at SemEval-2023 Task 4: Leveraging Pretrained Language Models for Human Value Argument Mining with Contrastive Learning
To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering
To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Togedemaru at SemEval-2023 Task 8: Causal Medical Claim Identification and Extraction from Social Media Posts
Together We Make Sense-Learning Meta-Sense Embeddings
Tokenization and the Noiseless Channel
Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages
Tokenization with Factorized Subword Encoding
Token-Level Self-Evolution Training for Sequence-to-Sequence Learning
Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions
TOME: A Two-stage Approach for Model-based Retrieval
Topic and Style-aware Transformer for Multimodal Emotion Recognition
Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection
Topic-Guided Self-Introduction Generation for Social Media Users
To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support
Toward Expanding the Scope of Radiology Report Summarization to Multiple Anatomies and Modalities
Toward Human-Like Evaluation for Natural Language Generation with Error Analysis
Toward Interactive Dictation
Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs
Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints
Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic Memory
Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning
Towards Alleviating the Object Bias in Prompt Tuning-based Factual Knowledge Extraction
Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking
Towards automatically extracting morphosyntactical error patterns from L1-L2 parallel dependency treebanks
Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
Towards Better Entity Linking with Multi-View Enhanced Distillation
Towards Better Hierarchical Text Classification with Data Generation
Towards Boosting the Open-Domain Chatbot with Human Feedback
Towards Building a Robust Toxicity Predictor
Towards Distribution-shift Robust Text Classification of Emotional Content
Towards Diverse and Effective Question-Answer Pair Generation from Children Storybooks
Towards Domain-Agnostic and Domain-Adaptive Dementia Detection from Spoken Language
Towards Efficient Dialogue Processing in the Emergency Response Domain
Towards Faithful Dialogues via Focus Learning
Towards Fewer Hallucinations in Knowledge-Grounded Dialogue Generation via Augmentative and Contrastive Knowledge-Dialogue
Towards fine-tuning pre-trained language models with integer forward and backward propagation
Towards Flow Graph Prediction of Open-Domain Procedural Texts
Towards Generative Event Factuality Prediction
Towards Higher Pareto Frontier in Multilingual Machine Translation
Towards Identifying Fine-Grained Depression Symptoms from Memes
Towards Imperceptible Document Manipulations against Neural Ranking Models
Towards L2-friendly pipelines for learner corpora: A case of written production by L2-Korean learners
Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages
Towards Open Environment Intent Prediction

« prev Page 50/56 next »