总结 | ACL2022主会论文分类整理（三）

评估

• Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons

• AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages

• BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation

• Bias Mitigation in Machine Translation Quality Estimation

• CARETS: A Consistency And Robustness Evaluative Test Suite for VQA

• ChatMatch: Evaluating Chatbots by Autonomous Chat Tournaments

• CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation

• DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations

• Evaluating Factuality in Text Simplification

• FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework

• FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text Generation

• Generative Pretraining for Paraphrase Evaluation

• Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation

• Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text

• Just Rank: Rethinking Evaluation with Word and Sentence Similarities

• Logic Traps in Evaluating Attribution Scores

• Quantified Reproducibility Assessment of NLP Results

• ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension

• RoMe: A Robust Metric for Evaluating Natural Language Generation

• SRL4E – Semantic Role Labeling for Emotions: A Unified Evaluation Framework

• TruthfulQA: Measuring How Models Mimic Human Falsehoods

• Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation

• UniTE: Unified Translation Evaluation

Sentence-level Semantics, Textual Classification, and Other Areas【句子级语义和文本关系推理】

• Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification

• Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis

• Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP

• Cluster & Tune: Boost Cold Start Performance in Text Classification

• Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis

• Early Stopping Based on Unlabeled Samples in Text Classification

• Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis

• Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction

• Entailment Graph Learning with Textual Entailment and Soft Transitivity

• Evaluating Extreme Hierarchical Multi-label Classification

• FaiRR: Faithful and Robust Deductive Reasoning over Natural Language

• Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation

• Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification

• KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling

• Label Semantic Aware Pre-training for Few-shot Text Classification

• Learn to Adapt for Generalized Zero-Shot Text Classification

• Leveraging Task Transferability to Meta-learning for Clinical Section Classification with Limited Data

• Measuring Fairness of Text Classifiers via Prediction Sensitivity

• On the Robustness of Offensive Language Classifiers

• Toward Interpretable Semantic Textual Similarity via Optimal Transportbased Contrastive Sentence Learning

• Towards Comprehensive Patent Approval Predictions:Beyond Traditional Document Classification

Semantics and Syntax Parsing【语义与句法解析】

语义解析

• LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing

• Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation

• Graph Pre-training for AMR Parsing and Generation

• LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing

• Learned Incremental Representations for Parsing

• Learning to Generate Programs for Table Fact Verification via StructureAware Semantic Parsing

• Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture Models

• On The Ingredients of an Effective Zero-shot Semantic Parser

• Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations

• Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation

• Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embedding
• 
  

句法分析

• Investigating Non-local Features for Neural Constituency Parsing

• Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks

• Compositional Generalization in Dependency Parsing

• Dependency Parsing as MRC-based Span-Span Prediction

• Headed-Span-Based Projective Dependency Parsing

• Investigating Non-local Features for Neural Constituency Parsing

• Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

• Phrase-aware Unsupervised Constituency Parsing

• Probing for Labeled Dependency Trees

• Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network

• Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing

• TwittIrish: A Universal Dependencies Treebank of Tweets in Modern Irish

• Unsupervised Dependency Graph Network

命名实体识别

• CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning

• De-Bias for Generative Extraction in Unified NER Task

• Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning

• Few-Shot Class-Incremental Learning for Named Entity Recognition

• Few-shot Named Entity Recognition with Self-describing Networks

• Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER

• MELM: Data Augmentation with Masked Entity Language Modeling for LowResource NER

• MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective

• Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing

• Nested Named Entity Recognition with Span-level Graphs

• Parallel Instance Query Network for Named Entity Recognition

指代消解

• Adapting Coreference Resolution Models through Active Learning

• Constrained Multi-Task Learning for Bridging Resolution

实体识别，对齐与消歧

• ExtEnD: Extractive Entity Disambiguation

• FiNER: Financial Numeric Entity Recognition for XBRL Tagging

• Learning from Sibling Mentions with Scalable Graph Inference in FineGrained Entity Typing

• An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism

• Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction

其它

• A Neural Network Architecture for Program Understanding Inspired by Human Behaviors

• Bridging the Generalization Gap in Text-to-SQL Parsing with Schema Expansion

• Fair and Argumentative Language Modeling for Computational Argumentation

• LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution

• Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages

• Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution

Speech and Multimodality【语音与多模态】

多模态

• Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas

• CARETS: A Consistency And Robustness Evaluative Test Suite for VQA

• CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment

• Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations

• End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding

• Guided Attention Multimodal Multitask Financial Forecasting with InterCompany Relationships and Global and Local News

• Image Retrieval from Contextual Descriptions

• Letters From the Past: Modeling Historical Sound Change Through Diachronic Character Embeddings

• Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-Modal Knowledge Transfer

• Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension

• Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network

• Multimodal Dialogue Response Generation

• Multimodal fusion via cortical network inspired losses

• Multimodal Sarcasm Target Identification in Tweets

• On Vision Features in Multimodal Machine Translation

• OpenHands: Making Sign Language Recognition Accessible with Posebased Pretrained Models across Languages

• Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of Data

• Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues

• RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining

• There’s a Time and Place for Reasoning Beyond the Image

• Things not Written in Text: Exploring Spatial Commonsense from Visual Signals

• Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals

• UniTranSeR: A Unified Transformer Semantic Representation Framework for Multimodal Task-Oriented Dialog System

• Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions

• Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis

• Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

• WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types

语音

• Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech

• Decoding Part-of-Speech from Human EEG Signals

• Direct Speech-to-Speech Translation With Discrete Units

• Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features

• Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

• Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization

• Revisiting Over-Smoothness in Text to Speech

• Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition

• SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

• STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation

• Text-Free Prosody-Aware Generative Spoken Language Modeling

• Do self-supervised speech models develop human-like perception biases?

Summation【摘要】

• A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization

• A Variational Hierarchical Model for Neural Cross-Lingual Summarization

• ASPECTNEWS: Aspect-Oriented Summarization of News Documents

• Attention Temperature Matters in Abstractive Summarization Distillation

• BRIO: Bringing Order to Abstractive Summarization

• Chart-to-Text: A Large-Scale Benchmark for Chart Summarization

• Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization

• Discriminative Marginalized Probabilistic Neural Method for Multi-Document Summarization of Medical Literature

• DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization

• Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-centric Summarization

• EntSUM: A Data Set for Entity-Centric Extractive Summarization

• Graph Enhanced Contrastive Learning for Radiology Findings Summarization

• Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

• HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization

• Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization

• Learning the Beauty in Songs: Neural Singing Voice Beautifier

• Length Control in Abstractive Summarization by Pretraining Information Selection

• MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes

• Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization

• Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions

• Predicting Intervention Approval in Clinical Trials through Multi-Document Summarization

• PRIMERA: Pyramid-based Masked Sentence Pre-training for Multidocument Summarization

• Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents

• SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization

• The patient is more dead than alive: exploring the current state of the multidocument summarisation of the biomedical literature

• Towards Abstractive Grounded Summarization of Podcast Transcripts

• Unsupervised Extractive Opinion Summarization Using Sparse Coding

• Updated Headline Generation: Creating Updated Summaries for Evolving News Stories

Knowledge Graph【知识图谱】

• CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion

• Efficient Hyper-parameter Search for Knowledge Graph Embedding

• KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base

• Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

• Prix-LM: Pretraining for Multilingual Knowledge Base Construction

• RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion

• Sequence-to-Sequence Knowledge Graph Completion and Question Answering

• SimKGC: Simple Contrastive Knowledge Graph Completion with Pretrained Language Models

• Understanding Gender Bias in Knowledge Base Embeddings

Special Track【特殊任务】

• Code Relevant

• Accelerating Code Search with Deep Hashing and Code Classification

• Impact of Evaluation Methodologies on Code Summarization

• Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization

• Towards Learning (Dis)-Similarity of Source Code from Program Contrasts

• UniXcoder: Unified Cross-Modal Pre-training for Code Representation

• ReACC: A Retrieval-Augmented Code Completion Framework

• Impact of Evaluation Methodologies on Code Summarization

• Math Problem

• Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction

• Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network

• NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks

• Word / Sentence Segmentation

• Weakly Supervised Word Segmentation for Computational Language Documentation

• Word Segmentation as Unsupervised Constituency Parsing

• That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory

• TopWORDS-Seg: Simultaneous Text Segmentation and Word Discovery for Open-Domain Chinese Texts via Bayesian Inference

• Others

• Automated Crossword Solving

• CaMEL: Case Marker Extraction without Labels

• Characterizing Idioms: Conventionality and Contingency

• Challenges and Strategies in Cross-Cultural NLP

• Clickbait Spoiling via Question Answering and Passage Retrieval

• Computational Historical Linguistics and Language Diversity in South Asia

• Doctor Recommendation in Online Health Forums via Expertise Learning

• Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction

• Entity-based Neural Local Coherence Modeling

• Ethics Sheets for AI Tasks

• HOLM: Hallucinating Objects with Language Models for Referring Expression Recognition in Partially-Observed Scenes

• Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing Annotations

• Identifying Moments of Change from Longitudinal User Text

• Identifying the Human Values behind Arguments

• Improving the Generalizability of Depression Detection by Leveraging Clinical Questionnaires

• Incorporating Stock Market Signals for Twitter Stance Detection

• Inferring Rewards from Language in Context

• Large Scale Substitution-based Word Sense Induction

• Learning From Failure: Data Capture in an Australian Aboriginal Community

• Leveraging Similar Users for Personalized Language Modeling with Limited Data

• Leveraging Wikipedia article evolution for promotional tone detection

• Misinfo Reaction Frames: Reasoning about Readers’ Reactions to News Headlines

• Multilingual Detection of Personal Employment Status on Twitter

• Not always about you: Prioritizing community needs when developing endangered language technology

• Perceiving the World: Question-guided Reinforcement Learning for Text-based Games

• Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection

• Searching for fingerspelled content in American Sign Language

• Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang

• Toward Annotator Group Bias in Crowdsourcing

• Towards Afrocentric NLP for African Languages: Where We Are and Where We Can Go

• Uncertainty Estimation of Transformer Predictions for Misclassification Detection

• VALUE: Understanding Dialect Disparity in NLU

• You might think about slightly revising the title: Identifying Hedges in Peertutoring Interactions

• A Functionalist Account of Vowel System Typology