来源: AINLPer公众号（每日干货分享！！）
编辑: ShuYini
校稿: ShuYini
时间: 2023-12-12

引言

EMNLP2023 于12月10日在新加坡落下帷幕，此次会议顺利举行。今年EMNLP2023 的投稿论文数量将近5000篇，长论文接收率为23.3%，短论文接收率为14%，整体接收率为21.3%。

下面是作者整理的短篇论文接受列表，因平台限制不能给出每篇论文的连接。如果有需要，欢迎关注 AINLPer公众号 回复：EMNLP2023 获取。

ENMLP2023 短篇论文接受列表

001、Fine-grained Conversational Decoding via Isotropic and Proximal Search
002、Primacy Effect of ChatGPT
003、Better Quality Pre-training Data and T5 Models for African Languages
004、Establishing Trustworthiness: Rethinking Tasks and Model Evaluation
005、Bootstrapping Small & High Performance Language Models with Unmasking-Removal Training Policy
006、Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation
007、Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models
008、Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings
009、Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation
010、Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation
011、PEFTDebias : Capturing debiasing information using PEFTs
012、ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation
013、VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining
014、Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning
015、Did You Mean…? Confidence-based Trade-offs in Semantic Parsing
016、Understanding the Effect of Model Compression on Social Bias in Large Language Models
017、Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling
018、Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation
019、Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques
020、Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies
021、GROOViST: A Metric for Grounding Objects in Visual Storytelling
022、When Do Decompositions Help for Machine Reading?
023、Revisiting De-Identification of Electronic Medical Records: Evaluation of Within- and Cross-Hospital Generalization
024、Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?
025、Are All Steps Equally Important? Benchmarking Essentiality Detection in Event Processes
026、ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision
027、Uncertainty Guided Global Memory Improves Multi-Hop Question Answering
028、Knowledge Distillation {$\approx$} Label Smoothing: Fact or Fallacy?
029、Analyzing Cognitive Plausibility of Subword Tokenization
030、POE: Process of Elimination for Multiple Choice Reasoning
031、Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis
032、Best of Both Worlds: Towards Improving Temporal Knowledge Base Question Answering via Targeted Fact Extraction
033、Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?
034、GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
035、BiasX: ``Thinking Slow’’ in Toxic Content Moderation with Explanations of Implied Social Biases
036、Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks
037、MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments
038、Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
039、Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models
040、EntSUMv2: Dataset, Models and Evaluation for More Abstractive Entity-Centric Summarization
041、Analysing State-Backed Propaganda Websites: a New Dataset and Linguistic Study
042、HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts
043、ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models
044、Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
045、Spoiler Detection as Semantic Text Matching
046、Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods
047、BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages
048、4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees
049、Pre-Trained Language Models Augmented with Synthetic Scanpaths for Natural Language Understanding
050、Understanding the Inner-workings of Language Models Through Representation Dissimilarity
051、Efficient Classification of Long Documents via State-Space Models
052、Construction Artifacts in Metaphor Identification Datasets
053、EtiCor: Corpus for Analyzing LLMs for Etiquettes
054、Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning
055、UniMath: A Foundational and Multimodal Mathematical Reasoner
056、Simple Temporal Adaptation to Changing Label Sets: Hashtag Prediction via Dense KNN
057、A Study on Accessing Linguistic Information in Pre-Trained Language Models by Using Prompts
058、Copyright Violations and Large Language Models
059、Somali Information Retrieval Corpus: Bridging the Gap between Query Translation and Dedicated Language Resources
060、Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT
061、Faithful Model Evaluation for Model-Based Metrics
062、Language Model Quality Correlates with Psychometric Predictive Power in Multiple Languages
063、Enhancing Code-Switching for Cross-lingual SLU: A Unified View of Semantic and Grammatical Coherence
064、M${}^3$Seg: A Maximum-Minimum Mutual Information Paradigm for Unsupervised Topic Segmentation in ASR Transcripts
065、GD-COMET: A Geo-Diverse Commonsense Inference Model
066、PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering
067、SOUL: Towards Sentiment and Opinion Understanding of Language
068、Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks
069、Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text
070、Exploring Linguistic Probes for Morphological Inflection
071、FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score
072、Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications
073、CLAD-ST: Contrastive Learning with Adversarial Data for Robust Speech Translation
074、Improved Unsupervised Chinese Word Segmentation Using Pre-trained Knowledge and Pseudo-labeling Transfer
075、Multilingual $k$-Nearest-Neighbor Machine Translation
076、Understanding Computational Models of Semantic Change: New Insights from the Speech Community
077、Revisiting Automated Topic Model Evaluation with Large Language Models
078、Query2doc: Query Expansion with Large Language Models
079、Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions
080、InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
081、Large Language Models are biased to overestimate profoundness
082、Prompting Scientific Names for Zero-Shot Species Recognition
083、MultiTurnCleanup: A Benchmark for Multi-Turn Spoken Conversational Transcript Cleanup
084、Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
085、Transformer-based Live Update Generation for Soccer Matches from Microblog Posts
086、Using Artificial French Data to Understand the Emergence of Gender Bias in Transformer Language Models
087、What do Deck Chairs and Sun Hats Have in Common? Uncovering Shared Properties in Large Concept Vocabularies
088、Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation
089、Polyglot or Not? Measuring Multilingual Encyclopedic Knowledge in Foundation Models
090、Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification
091、Data Similarity is Not Enough to Explain Language Model Performance
092、Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection
093、mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval
094、CodeFusion: A Pre-trained Diffusion Model for Code Generation
095、VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights
096、Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
097、Cabbage Sweeter than Cake? Analysing the Potential of Large Language Models for Learning Conceptual Spaces
098、Large-scale similarity search with Optimal Transport
099、FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning
100、Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification
101、Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems
102、CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks
103、Select, Prompt, Filter: Distilling Large Language Models for Summarizing Conversations
104、Human Raters Cannot Distinguish English Translations from Original English Texts
105、Faster Minimum Bayes Risk Decoding with Confidence-based Pruning
106、Revisiting Sparse Retrieval for Few-shot Entity Linking
107、Context Compression for Auto-regressive Transformers with Sentinel Tokens
108、Set Learning for Generative Information Extraction
109、Token Prediction as Implicit Classification to Identify LLM-Generated Text
110、On Evaluation of Bangla Word Analogies
111、Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents
112、CLAIR: Evaluating Image Captions with Large Language Models
113、Poisoning Retrieval Corpora by Injecting Adversarial Passages
114、Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix
115、SUT: Active Defects Probing for Transcompiler Models
116、This Reads Like That: Deep Learning for Interpretable Natural Language Processing
117、SMoP: Towards Efficient and Effective Prompt Tuning with Sparse Mixture-of-Prompts
118、Outlier Dimensions Encode Task Specific Knowledge
119、Self-Ensemble of $N$-best Generation Hypotheses by Lexically Constrained Decoding
120、Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
121、Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism
122、A Simple Baseline for Knowledge-Based Visual Question Answering
123、Unveiling the Essence of Poetry: Introducing a Comprehensive Dataset and Benchmark for Poem Summarization
124、CoRec: An Easy Approach for Coordination Recognition
125、FinEntity: Entity-level Sentiment Classification for Financial Texts
126、Rationale-Enhanced Language Models are Better Continual Relation Learners
127、Inverse Scaling Can Become U-Shaped
128、ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition
129、NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation
130、ClimateBERT-NetZero: Detecting and Assessing Net Zero and Reduction Targets
131、An Attribution Method for Siamese Encoders
132、Are Compressed Language Models Less Subgroup Robust?
133、Length Does Matter: Summary Length can Bias Summarization Metrics
134、Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation
135、Automated Fact-Checking in Dialogue: Are Specialized Models Needed?
136、Assessing the influence of attractor-verb distance on grammatical agreement in humans and language models
137、To Split or Not to Split: Composing Compounds in Contextual Vector Spaces
138、TaskDiff: A Similarity Metric for Task-Oriented Conversations
139、A Benchmark for Reasoning with Spatial Prepositions
140、Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation
141、MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding
142、PK-ICR: Persona-Knowledge Interactive Multi-Context Retrieval for Grounded Dialogue
143、A Self-training Framework for Automated Medical Report Generation
144、A Picture is Worth a Thousand Words: Language Models Plan from Pixels
145、Relation-aware Ensemble Learning for Knowledge Graph Embedding
146、When Reviewers Lock Horns: Finding Disagreements in Scientific Peer Reviews
147、Sandeep Kumar, Tirthankar Ghosal, Asif Ekbal