作者简介：唐天一，中国人民大学高瓴人工智能学院硕士一年级，导师为赵鑫教授，研究方向为自然语言处理。
导读
ACL-IJCNLP 2021是CCF A类会议，是人工智能领域自然语言处理（ Natural Language Processing，NLP）方向最权威的国际会议。计算语言学协会第59届年会暨第11届自然语言处理国际联席会议（The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021）计划于今年8月1日-8月6日以线上会议形式召开。本届ACL共计收到3350篇论文投稿，最终有21.3%的论文录用到主会，并额外接收了14.9%的论文到Findings子刊，综合录用率为36.2%，官方发布的接收论文列表：
其中主会接受了571篇长文，139篇短文，Findings接受了340篇长文，118篇短文，共计1168篇。上一篇文章中我们选取了571篇主会长文进行了分类整理：
本篇文章继续对139篇主会短文和458篇Findings长短文进行了分类整理。文章也同步发布在AI Box微信公众号（微信搜索「 RUC AI Box」），整理过程中难免有疏漏，欢迎大家在知乎专栏的文章下方评论留言，交流探讨！
对抗攻击和鲁棒性
主会短文
Improving Arabic Diacritization with Regularized Decoding and Adversarial Training
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter
Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models
Robust Transfer Learning with Pretrained Language Models through Adapters
Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning
Findings长文
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling
OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack
Contrastive Fine-tuning Improves Robustness for Neural Rankers
Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning
BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks
A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples
Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification
BERT Busters: Outlier Dimensions that Disrupt Transformers
Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation
HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation
Findings短文
Decoupling Adversarial Training for Fair NLP
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning
End-to-End Self-Debiasing Framework for Robust NLU Training
Manifold Adversarial Augmentation for Neural Machine Translation
道德与自然语言处理
主会短文
What’s in the Box? An Analysis of Undesirable Content in the Common Crawl Corpus
How effective is BERT without word ordering? Implications for language understanding and data privacy
Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models
Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia
Gender bias amplification during Speed-Quality optimization in Neural Machine Translation
On Positivity Bias in Negative Reviews
Findings长文
The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification
Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech
A Mixed-Method Design Approach for Empirically Based Selection of Unbiased Data Annotators
On the Interaction of Belief Bias and Explanations
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation
On the Ethical Limits of Natural Language Processing on Legal Text
Differential Privacy for Text Analytics via Natural Text Sanitization
Analyzing Stereotypes in Generative Text Inference Tasks
Marked Attribute Bias in Natural Language Inference
Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence
An Investigation of Suitability of Pre-Trained Language Models for Dialogue Generation – Avoiding Discrepancies
He is very intelligent, she is very beautiful? On Mitigating Social Biases in Language Modelling and Generation
On the Language Coverage Bias for Neural Machine Translation
John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs
Findings短文
An Exploratory Analysis of the Relation between Offensive Language and Mental Health
Use of Formal Ethical Reviews in NLP Literature: Historical Trends and Current Practices
对话系统
主会短文
Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking
Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking
On the Generation of Medical Dialogs for COVID-19
Domain-Adaptive Pretraining Methods for Dialogue Understanding
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images
PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation
Unsupervised Enrichment of Persona-grounded Dialog with Background Stories
Findings长文
GoG: Relation-aware Graph-over-Graph Network for Visual Dialog
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots
Scheduled Dialog Policy Learning: An Automatic Curriculum Learning Framework for Task-oriented Dialog System
Survival text regression for time-to-event prediction in conversations
Unsupervised Knowledge Selection for Dialogue Generation
Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study
HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management
Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning
“Does it Matter When I Think You Are Lying?” Improving Deception Detection by Integrating Interlocutor’s Judgements in Conversations
High-Quality Dialogue Diversification by Intermittent Short Extension Ensembles
REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
Dialogue-oriented Pre-training
Knowledge-Grounded Dialogue Generation with Term-level De-noising
Dialogue Graph Modeling for Conversational Machine Reading
An Investigation of Suitability of Pre-Trained Language Models for Dialogue Generation – Avoiding Discrepancies
Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation
Findings短文
Assessing Dialogue Systems with Distribution Distances
Summary Grounded Conversation Generation
Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation
Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
会话、语用与论证挖掘
主会短文
Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese
Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models
Findings长文
LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification
Counter-Argument Generation by Attacking Weak Premises
文本生成
主会短文
AligNarr: Aligning Narratives on Movies
Zero-shot Fact Verification by Claim Generation
Learning to Generate Task-Specific Adapters from Task Description
On Training Instance Selection for Few-Shot Neural Text Generation
How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation?
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
Question Generation for Adaptive Education
Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data
Avoiding Overlap in Data Augmentation for AMR-to-Text Generation
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer
Findings长文
Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech
Contrastive Attention for Automatic Chest X-ray Report Generation
Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech
Promoting Graph Awareness in Linearized Graph-to-Text Generation
On-the-Fly Attention Modulation for Neural Generation
Detecting Hallucinated Content in Conditional Neural Sequence Generation
Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
Automatic Document Sketching: Generating Drafts from Analogous Texts
Learning Shared Semantic Space for Speech-to-Text Translation
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models
Provably Secure Generative Linguistic Steganography
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
IgSEG: Image-guided Story Ending Generation
Probabilistic Graph Reasoning for Natural Proof Generation
Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction
Logic-Consistency Text Generation from Semantic Parses
Investigating Memorization of Conspiracy Theories in Text Generation
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation
TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation
Generalized Supervised Attention for Text Generation
Findings短文
Structure-Aware Pre-Training for Table-to-Text Generation
Stylized Story Generation with Style-Guided Planning
Enhancing Language Generation with Effective Checkpoints of Pre-trained Language Model
Retrieval Enhanced Model for Commonsense Generation
Analysis of Tree-Structured Architectures for Code Generation
信息抽取
主会短文
TIMERS: Document-level Temporal Relation Extraction
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
Enhancing Entity Boundary Detection for Better Chinese Named Entity Recognition
Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking
Entity Concept-enhanced Few-shot Relation Extraction
Improving Model Generalization: A Chinese Named Entity Recognition Case Study
MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network
Explicitly Capturing Relations between Entity Mentions via Graph Neural Networks for Domain-specific Named Entity Recognition
Zero-shot Event Extraction via Transfer Learning: Challenges and Insights
A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
Findings长文
Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
From What to Why: Improving Relation Extraction with Rationale Graph
CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction
Link Prediction on N-ary Relational Facts: A Graph-based Approach
SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction
KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction
Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking
A Dialogue-based Information Extraction System for Medical Insurance Assessment
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction
OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction
MRN: A Locally and Globally Mention-Based Reasoning Network for Document-Level Relation Extraction
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction
Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition
Event Detection as Graph Parsing
Toward Fully Exploiting Heterogeneous Corpus: A Decoupled Named Entity Recognition Model with Two-stage Training
Discriminative Reasoning for Document-level Relation Extraction
Template-Based Named Entity Recognition Using BART
End-to-End Construction of NLP Knowledge Graph
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection
Relation Extraction with Type-aware Map Memories of Word Dependencies
OKGIT: Open Knowledge Graph Link Prediction with Implicit Types
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction
Paths to Relation Extraction through Semantic Structure
GrantRel: Grant Information Extraction via Joint Entity and Relation Extraction
Energy-based Unknown Intent Detection with Data Manipulation
Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning
Effective Cascade Dual-Decoder Model for Joint Entity and Relation Extraction
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures
Towards Protecting Vital Healthcare Programs by Extracting Actionable Knowledge from Policy
Biomedical Interpretable Entity Representations
Transforming Term Extraction: Transformer-Based Approaches to Multilingual Term Extraction Across Domains
Named Entity Recognition through Deep Representation Learning and Weak Supervision
Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction
The Utility and Interplay of Gazetteers and Entity Segmentation for Named Entity Recognition in English
Unsupervised Domain Adaptation for Event Detection using Domain-specific Adapters
Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text
MLMLM: Link Prediction with Mean Likelihood Masked Language Model
Constrained Labeled Data Generation for Low-Resource Named Entity Recognition
Automatic Construction of Sememe Knowledge Bases via Dictionaries
Named Entity Recognition via Noise Aware Training Mechanism with Data Filter
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information
Findings短文
Relation Classification with Entity Type Restriction
Cross-Lingual Cross-Domain Nested Named Entity Evaluation on English Web Texts
Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics
A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction
Neural Entity Recognition with Gazetteer based Fusion
Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction
Enhancing Dialogue-based Relation Extraction by Speaker and Trigger Words Prediction
信息检索与文本挖掘
主会短文
The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes
Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation
Findings长文
Weakly Supervised Pre-Training for Multi-Hop Retriever
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference
Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation
Findings短文
Retrieval Enhanced Model for Commonsense Generation
自然语言处理模型的可解释性与分析
主会短文
Attention Flows are Shapley Value Explanations
Is Sparse Attention more Interpretable?
Findings长文
Meet The Truth: Leverage Objective Facts and Subjective Views for Interpretable Rumor Detection
Enhancing Metaphor Detection by Gloss-based Interpretations
FrameNet-assisted Noun Compound Interpretation
Using surprisal and fMRI to map the neural bases of broad and local contextual prediction during natural language comprehension
Explaining NLP Models via Minimal Contrastive Editing (MiCE)
Findings短文
How Reliable are Model Diagnostics?
Do Language Models Perform Generalizable Commonsense Inference?
On the Lack of Robust Interpretability of Neural Text Classifiers
Effective Attention Sheds Light On Interpretability
How transfer learning impacts linguistic knowledge in deep NLP models?
语言模型
主会短文
Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling
The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models
AND does not mean OR: Using Formal Languages to Study Language Models’ Representations
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?
Robust Transfer Learning with Pretrained Language Models through Adapters
Findings长文
REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training
AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization
Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages
LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
Training ELECTRA Augmented with Multi-word Selection
MergeDistill: Merging Language Models using Pre-trained Distillation
Inspecting the concept knowledge graph encoded by modern language models
Probing Pre-Trained Language Models for Disease Knowledge
“We will Reduce Taxes” - Identifying Election Pledges with Language Models
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level
Learning to Sample Replacements for ELECTRA Pre-Training
Fingerprinting Fine-tuned Language Models in the Wild
Language Models Use Monotonicity to Assess NPI Licensing
Findings短文
More Parameters? No Thanks!
Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
Modulating Language Models with Emotions
One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers
Task-adaptive Pre-training of Language Models with Word Embedding Regularization
词法
主会短文
A Mixture-of-Experts Model for Antonym-Synonym Discrimination
Findings长文
Hypernym Discovery via a Recurrent Mapping Model
语言理论、认知建模和心理语言学
Findings长文
Rationalization through Concepts
Enhanced Metaphor Detection via Incorporation of External Knowledge Based on Linguistic Theories
Detecting Harmful Memes and Their Targets
自然语言处理机器学习
主会短文
Parameter Selection: Why We Should Pay More Attention to It
Attentive Multiview Text Representation for Differential Diagnosis
Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event
Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
Higher-order Derivatives of Weighted Finite-state Machines
On Orthogonality Constraints for Transformers
Continual Quality Estimation with Online Bayesian Meta-Learning
Relative Importance in Sentence Processing
Replicating and Extending ``Because Their Treebanks Leak’’: Graph Isomorphism, Covariants, and Parser Performance
VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension
DefSent: Sentence Embeddings using Definition Sentences
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence
Learning to Solve NLP Tasks in an Incremental Number of Languages
Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?
Robust Transfer Learning with Pretrained Language Models through Adapters
Discrete Cosine Transform as Universal Sentence Encoder
A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space
Findings长文
LV-BERT: Exploiting Layer Variety for BERT
Joint Optimization of Tokenization and Downstream Model
How does Attention Affect the Model?
RealFormer: Transformer Likes Residual Attention
A Survey of Data Augmentation Approaches for NLP
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?
Minimax and Neyman-Pearson Meta-Learning for Outlier Languages
Incorporating Global Information in Local Attention for Knowledge Representation Learning
Documents Representation via Generalized Coupled Tensor Chain with the Rotation Group constraint
Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene
A Query-Driven Topic Model
Language-Mediated, Object-Centric Representation Learning
Language-based General Action Template for Reinforcement Learning Agents
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers
Attending via both Fine-tuning and Compressing
Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources
On the Interplay Between Fine-tuning and Composition in Transformers
Lifelong Learning of Topics and Domain-Specific Word Embeddings
Graph Relational Topic Model with Higher-order Graph Attention Auto-encoders
Insertion-based Tree Decoding
Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax
Perceptual Models of Machine-Edited Text
Memory-Efficient Differentiable Transformer Architecture Search
Disentangled Code Representation Learning for Multiple Programming Languages
Reordering Examples Helps during Priming-based Few-Shot Learning
Findings短文
More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods
Learning Slice-Aware Representations with Mixture of Attentions
RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations
Fusion: Towards Automated ICD Coding via Feature Compression
MA-BERT: Learning Representation by Incorporating Multi-Attribute Knowledge in Transformers
Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment
DoT: An efficient Double Transformer for NLP tasks with tables
Modeling the Unigram Distribution
Sequence Models for Computational Etymology of Borrowings
Benchmarking Neural Topic Models: An Empirical Study
BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch
Knowledge Distillation for Quality Estimation
机器翻译与多语言
主会短文
BERTTune: Fine-Tuning Neural Machine Translation with BERTScore
Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation
Adaptive Nearest Neighbor Machine Translation
Anchor-based Bilingual Word Embeddings for Low-Resource Languages
An Exploratory Analysis of Multilingual Word-Level Quality Estimation with Cross-Lingual Transformers
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?
Multilingual Agreement for Multilingual Neural Machine Translation
mTVR: Multilingual Moment Retrieval in Videos
Machine Translation into Low-resource Language Varieties
Don’t Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data
Findings长文
Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
XeroAlign: Zero-shot cross-lingual transformer alignment
Can Cognate Prediction Be Modelled as a Low-Resource Machine Translation Task?
Predicting cross-linguistic adjective order with information gain
Multi-Granularity Contrasting for Cross-Lingual Pre-Training
A Comparison between Pre-training and Large-scale Back-translation for Neural Machine Translation
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation
Pipeline Signed Japanese Translation Focusing on a Post-positional Particle Complement and Conjugation in a Low-resource Setting
Multi-Lingual Question Generation with Language Agnostic Language Model
Confidence-Aware Scheduled Sampling for Neural Machine Translation
Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation
Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation
Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction
Exploring Unsupervised Pretraining Objectives for Machine Translation
AugVic: Exploiting BiText Vicinity for Low-Resource NMT
Multilingual Translation from Denoising Pre-Training
Probing Multi-modal Machine Translation with Pre-trained Language Model
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference
Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models
On the Copying Behaviors of Pre-Training for Neural Machine Translation
XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages
Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan
Findings短文
Encouraging Neural Machine Translation to Satisfy Terminology Constraints
Alternated Training with Synthetic and Authentic Data for Neural Machine Translation
Progressive Multi-Granularity Training for Non-Autoregressive Translation
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?
Language Tags Matter for Zero-Shot Neural Machine Translation
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation
Multilingual Simultaneous Neural Machine Translation
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High
自然语言处理应用
主会短文
Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain
Catchphrase: Automatic Detection of Cultural References
On the Generation of Medical Dialogs for COVID-19
Weakly-Supervised Methods for Suicide Risk Assessment: Role of Related Domains
Quantifying and Avoiding Unfair Qualification Labour in Crowdsourcing
Question Generation for Adaptive Education
Quotation Recommendation and Interpretation Based on Transformation from Queries to Quotations
Happy Dance, Slow Clap: Using Reaction GIFs to Predict Induced Affect on Twitter
Automatic Fake News Detection: Are Models Learning to Reason?
Findings长文
LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification
Medical Code Assignment with Gated Convolution and Note-Code Interaction
Learning Algebraic Recombination for Compositional Generalization
RevCore: Review-Augmented Conversational Recommendation
Adversary-Aware Rumor Detection
CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding
Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate
Studying the Evolution of Scientific Topics and their Relationships
Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading
A Multi-Level Attention Model for Evidence-Based Fact Checking
Multimodal Fusion with Co-Attention Networks for Fake News Detection
Automatic Text Simplification for Social Good: Progress and Challenges
When Time Makes Sense: A Historically-Aware Approach to Targeted Sense Disambiguation
Automatic Rephrasing of Transcripts-based Action Items
How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact
Biomedical Interpretable Entity Representations
Implications of Using Internet Sting Corpora to Approximate Underage Victims
Analyzing Online Political Advertisements
Constructing Flow Graphs from Procedural Cybersecurity Texts
A Formidable Ability: Detecting Adjectival Extremeness with DSMs
SMS Spam Detection Through Skip-gram Embeddings and Shallow Networks
Exploring Self-Identified Counseling Expertise in Online Support Forums
Using Social and Linguistic Information to Adapt Pretrained Representations for Political Perspective Identification
What Would a Teacher Do? Predicting Future Talk Moves
Findings短文
Using Word Embeddings to Analyze Teacher Evaluations: An Application to a Filipino Education Non-Profit Organization
Modeling the Influence of Verb Aspect on the Activation of Typical Event Locations with BERT
Few-Shot Upsampling for Protest Size Detection
Predicting in-hospital mortality by combining clinical notes with time-series data
Analyzing Code Embeddings for Coding Clinical Narratives
Characterizing Social Spambots by their Human Traits
音韵学、形态学和分词
主会短文
When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation
More than Text: Multi-modal Chinese Word Segmentation
Findings长文
Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation
Sensei: Self-Supervised Sensor Name Segmentation
IndoCollex: A Testbed for Morphological Transformation of Indonesian Word Colloquialism
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation
Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability
Findings短文
Better Chinese Sentence Segmentation with Reinforcement Learning
Federated Chinese Word Segmentation with Global Character Associations
问答
主会短文
Towards a more Robust Evaluation for Conversational Question Answering
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints
Multi-Scale Progressive Attention Network for Video Question Answering
Efficient Passage Retrieval with Hashing for Open-domain Question Answering
Towards Visual Question Answering on Pathology Images
QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining
Towards more equitable question answering systems: How much more data do you need?
A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering
Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation
Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering
Findings长文
Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering
Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations
Controlling Text Edition by Changing Answers of Specific Questions
Learning to Generate Questions by Learning to Recover Answer-containing Sentences
Knowing More About Questions Can Help: Improving Calibration in Question Answering
Multi-Lingual Question Generation with Language Agnostic Language Model
Latent Reasoning for Low-Resource Question Generation
WeaQA: Weak Supervision via Captions for Visual Question Answering
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Cluster-Former: Clustering-based Sparse Transformer for Question Answering
Findings短文
Reader-Guided Passage Reranking for Open-Domain Question Answering
Fusing Context Into Knowledge Graph for Commonsense Question Answering
Is Human Scoring the Best Criteria for Summary Evaluation?
Answer Generation for Retrieval-based Question Answering Systems
数据集、资源和评估
主会短文
DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
Targeting the Benchmark: On Methodology in Current Natural Language Processing Research
Towards a more Robust Evaluation for Conversational Question Answering
What Motivates You? Benchmarking Automatic Detection of Basic Needs from Short Posts
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images
WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation
OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres
Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test
Difficulty-Aware Machine Translation Evaluation
X-Fact: A New Benchmark Dataset for Multilingual Fact Checking
Findings长文
WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections
GLGE: A New General Language Generation Evaluation Benchmark
TellMeWhy: A Dataset for Answering Why-Questions in Narratives
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences
SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification
Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency
Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations
GCRC: A New Challenging MRC Dataset from Gaokao Chinese for Explainable Evaluation
PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate
An Evaluation of Disentangled Representation Learning for Texts
Evaluating Word Embeddings with Categorical Modularity
Entheos: A Multimodal Dataset for Studying Enthusiasm
GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoning
P-Stance: A Large Dataset for Stance Detection in Political Domain
DocOIE: A Document-level Context-Aware Dataset for OpenIE
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection
REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation
GEM: A General Evaluation Benchmark for Multimodal Tasks
HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications
Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering
How well do you know your summarization datasets?
Substructure Substitution: Structured Data Augmentation for NLP
The interplay between language similarity and script on a novel multi-layer Algerian dialect corpus
Revisiting the Evaluation of End-to-end Event Extraction
Enhancing the Open-Domain Dialogue Evaluation in Latent Space
DocNLI: A Large-scale Dataset for Document-level Natural Language Inference
DialogSum: A Real-Life Scenario Dialogue Summarization Dataset
What Did You Refer to? Evaluating Co-References in Dialogue
Findings短文
CoDesc: A Large Code-Description Parallel Dataset
GO FIGURE: A Meta Evaluation of Factuality in Summarization
Benchmarking Robustness of Machine Reading Comprehension Models
Investigating Text Simplification Evaluation
Annotation and Evaluation of Coreference Resolution in Screenplays
Event Extraction from Historical Texts: A New Dataset for Black Rebellions
Is the Lottery Fair? Evaluating Winning Tickets Across Demographics
New Dataset and Strong Baselines for the Grammatical Error Correction of Russian
PSED: A Dataset for Selecting Emphasis in Presentation Slides
句子级语义和文本推理
主会短文
Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models
Measuring and Improving BERT’s Mathematical Abilities by Predicting the Order of Reasoning.
MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain
Enforcing Consistency in Weakly Supervised Semantic Parsing
Embracing Ambiguity: Shifting the Training Target of NLI Models
Exploring Listwise Evidence Reasoning with T5 for Fact Verification
Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering
Neural-Symbolic Commonsense Reasoner with Relation Predictors
Findings长文
Explainable Inference Over Grounding-Abstract Chains for Science Questions
SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics
Discovering Topics in Long-tailed Corpora with Causal Intervention
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Prediction or Comparison: Toward Interpretable Qualitative Reasoning
On Commonsense Cues in BERT for Solving Commonsense Tasks
Hashing based Efficient Inference for Image-Text Matching
RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge
Are Rotten Apples Edible? Challenging Commonsense Inference Ability with Exceptions
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
Learning Shared Semantic Space for Speech-to-Text Translation
Empowering Language Understanding with Counterfactual Reasoning
Joint Multi-Decoder Framework with Hierarchical Pointer Network for Frame Semantic Parsing
Understanding Feature Focus in Multitask Settings for Lexico-semantic Relation Identification
Latent Reasoning for Low-Resource Question Generation
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference
It’s All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference
Learning Contextualized Knowledge Structures for Commonsense Reasoning
Analyzing Stereotypes in Generative Text Inference Tasks
Prompting Contrastive Explanations for Commonsense Reasoning Tasks
Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction
Inducing Semantic Roles Without Syntax
Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning
PROST: Physical Reasoning about Objects through Space and Time
EBERT: Efficient BERT Inference with Dynamic Structured Pruning
Findings短文
Diagnosing Transformers in Task-Oriented Semantic Parsing
Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics
Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
Figurative Language in Recognizing Textual Entailment
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers
Rule-Aware Reinforcement Learning for Knowledge Graph Reasoning
Strong and Light Baseline Models for Fact-Checking Joint Inference
Could you give me a hint ? Generating inference graphs for defeasible reasoning
情感分析、文体分析
主会短文
Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition
Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis
Towards Generative Aspect-Based Sentiment Analysis
eMLM: A New Pre-training Objective for Emotion Related Tasks
Findings长文
DNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction
Leveraging Argumentation Knowledge Graph for Interactive Argument Pair Identification
Dynamic and Multi-Channel Graph Convolutional Networks for Aspect-Based Sentiment Analysis
Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis
Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon
A Text-Centered Shared-Private Framework via Cross-Modal Prediction for Multimodal Sentiment Analysis
Cross-Domain Review Generation for Aspect-Based Sentiment Analysis
Automatically Select Emotion for Response via Personality-affected Emotion Transition
Findings短文
Boundary Detection with BERT for Span-level Emotion Cause Analysis
Exploiting Position Bias for Robust Aspect Sentiment Classification
Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning
UserAdapter: Few-Shot User Learning in Sentiment Analysis
Minimally-Supervised Morphological Segmentation using Adaptor Grammars with Linguistic Priors
Leveraging Topic Relatedness for Argument Persuasion
语音与多模态
主会短文
Beyond Laurel/Yanny: An Autoencoder-Enabled Search for Polyperceivable Audio
Enhancing Descriptive Image Captioning with Natural Language Inference
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images
An Improved Model for Voicing Silent Speech
Lightweight Adapter Tuning for Multilingual Speech Translation
mTVR: Multilingual Moment Retrieval in Videos
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses
Findings长文
Semantic Relation-aware Difference Representation Learning for Change Captioning
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Deep Learning against COVID-19: Respiratory Insufficiency Detection in Brazilian Portuguese Speech
Parallel Attention Network with Sequence Matching for Video Grounding
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate
Attention-based Contextual Language Model Adaptation for Speech Recognition
RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer
Learning Robust Latent Representations for Controllable Speech Synthesis
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation
Probing Image-Language Transformers for Verb Understanding
Probing Multi-modal Machine Translation with Pre-trained Language Model
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction
Compositionality of Complex Graphemes in the Undeciphered Proto-Elamite Script using Image and Text Embedding Models
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
Plot and Rework: Modeling Storylines for Visual Storytelling
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights
Findings短文
Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation
Transformer-Exclusive Cross-Modal Representation for Vision and Language
Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR
文本摘要
主会短文
Video Paragraph Captioning as a Text Summarization Task
Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards
Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization
Findings长文
Entity-Aware Abstractive Multi-Document Summarization
TransSum: Translating Aspect and Sentiment Embeddings for Self-Supervised Opinion Summarization
Code Summarization with Structure-induced Transformer
Improving Unsupervised Extractive Summarization with Facet-Aware Modeling
Contrastive Aligned Joint Learning for Multilingual Summarization
Learning Sequential and Structural Information for Source Code Summarization
A Joint Model for Structure-based News Genre Classification with Application to Text Summarization
To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text
AgreeSum: Agreement-Oriented Multi-Document Summarization
Generating Informative Conclusions for Argumentative Texts
A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification
Word Graph Guided Summarization for Radiology Findings
Controllable Abstractive Dialogue Summarization with Sketch Supervision
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification
Findings短文
LenAtten: An Effective Length Controlling Unit For Text Summarization
Evaluating the Efficacy of Summarization Evaluation across Languages
Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance
BioGen: Generating Biography Summary under Table Guidance on Wikipedia
Highlight-Transformer: Leveraging Key Phrase Aware Attention to Improve Abstractive Multi-Document Summarization
语法、标记和解析
主会短文
Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
Coreference Resolution without Span Representations
A Simple Recipe for Multilingual Grammatical Error Correction
Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction
Findings长文
Spatial Dependency Parsing for Semi-Structured Document Information Extraction
Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
What if This Modified That? Syntactic Interventions with Counterfactual Embeddings
Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing
Global Attention Decoder for Chinese Spelling Error Correction
Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing
Neural Combinatory Constituency Parsing
Correcting Chinese Spelling Errors with Phonetic Pre-training
Dynamic Connected Networks for Chinese Spelling Check
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
BERT-Proof Syntactic Structures: Investigating Errors in Discontinuous Constituency Parsing
Representing Syntax and Composition with Geometric Transformations
Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models
Scaling Within Document Coreference to Long Texts
Effective Batching for Recurrent Neural Network Grammars
Findings短文
Improving BERT with Syntax-aware Local Attention
Frustratingly Simple Few-Shot Slot Tagging
Grammar-Constrained Neural Semantic Parsing with LR Parsers
Grammar-Based Patches Generation for Automated Program Repair
Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution
Grammatical Error Correction as GAN-like Sequence Labeling
Minimally-Supervised Morphological Segmentation using Adaptor Grammars with Linguistic Priors
Do Grammatical Error Correction Models Realize Grammatical Generalization?
Domain-Aware Dependency Parsing for Questions
Climbing the Tower of Treebanks: Improving Low-Resource Dependency Parsing via Hierarchical Source Selection
Rule Augmented Unsupervised Constituency Parsing
Cross-document Coreference Resolution over Predicted Mentions
文本分类
主会短文
SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles
Cross-lingual Text Classification with Heterogeneous Graph Neural Network
Improving Compositional Generalization in Classification Tasks via Structure Annotations
Distinct Label Representations for Few-Shot Text Classification
Issues with Entailment-based Zero-shot Text Classification
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification
Findings长文
Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning
Unsupervised Energy-based Adversarial Domain Adaptation for Cross-domain Text Classification
Zero-shot Label-Aware Event Trigger and Argument Classification
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder
Don’t Miss the Labels: Label-semantic Augmented Meta-Learner for Few-Shot Text Classification
On the Cost-Effectiveness of Stacking of Neural and Non-Neural Methods for Text Classification: Scenarios and Performance Prediction
Unsupervised Label Refinement Improves Dataless Text Classification
Findings短文
BertGCN: Transductive Text Classification by Combining GNN and BERT
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification
A Multi-Task Learning Framework for Multi-Target Stance Detection
SSMix: Saliency-Based Span Mixup for Text Classification
Learning Disentangled Latent Topics for Twitter Rumour Veracity Classification
Uncertainty Aware Review Hallucination for Science Article Classification
其他
Findings长文
Why Machine Reading Comprehension Models Learn Shortcuts?
Structured Refinement for Sequential Labeling
WIND: Weighting Instances Differentially for Model-Agnostic Domain Adaptation
Annotations Matter: Leveraging Multi-task Learning to Parse UD and SUD
Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring
Grounding ‘Grounding’ in NLP
Semi-Supervised Data Programming with Subset Selection
Slot Transferability for Cross-domain Slot Filling
Findings短文
Can the Transformer Learn Nested Recursion with Symbol Masking?
On the Gap between Adoption and Understanding in NLP
Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection
Beyond Metadata: What Paper Authors Say About Corpora They Use