acl 2021 论文列表
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 2: Short Papers), Virtual Event, August 1-6, 2021.
|
Don't Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data.
Replicating and Extending "Because Their Treebanks Leak": Graph Isomorphism, Covariants, and Parser Performance.
Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents.
SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles.
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization.
Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test.
Weakly-Supervised Methods for Suicide Risk Assessment: Role of Related Domains.
Avoiding Overlap in Data Augmentation for AMR-to-Text Generation.
VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension.
Towards a more Robust Evaluation for Conversational Question Answering.
MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain.
Attentive Multiview Text Representation for Differential Diagnosis.
Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders.
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction.
Improving Model Generalization: A Chinese Named Entity Recognition Case Study.
Entity Concept-enhanced Few-shot Relation Extraction.
Efficient Passage Retrieval with Hashing for Open-domain Question Answering.
Multi-Scale Progressive Attention Network for Video Question Answering.
Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving.
DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications.
Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning.
Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction.
Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction.
Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain.
BERTTune: Fine-Tuning Neural Machine Translation with BERTScore.
Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection.
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images.
On the Generation of Medical Dialogs for COVID-19.
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking.
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning.
Embracing Ambiguity: Shifting the Training Target of NLI Models.
Robust Transfer Learning with Pretrained Language Models through Adapters.
Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling.
Learning to Solve NLP Tasks in an Incremental Number of Languages.
Distinct Label Representations for Few-Shot Text Classification.
Parameter Selection: Why We Should Pay More Attention to It.
Lightweight Adapter Tuning for Multilingual Speech Translation.
Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering.
What Motivates You? Benchmarking Automatic Detection of Basic Needs from Short Posts.
Neural-Symbolic Commonsense Reasoner with Relation Predictors.
Issues with Entailment-based Zero-shot Text Classification.
Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data.
Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese.
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence.
Quotation Recommendation and Interpretation Based on Transformation from Queries to Quotations.
Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction.
Explicitly Capturing Relations between Entity Mentions via Graph Neural Networks for Domain-specific Named Entity Recognition.
mTVR: Multilingual Moment Retrieval in Videos.
Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations.
Towards Visual Question Answering on Pathology Images.
A Simple Recipe for Multilingual Grammatical Error Correction.
Question Generation for Adaptive Education.
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?
X-Fact: A New Benchmark Dataset for Multilingual Fact Checking.
Targeting the Benchmark: On Methodology in Current Natural Language Processing Research.
Domain-Adaptive Pretraining Methods for Dialogue Understanding.
QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining.
Learning to Generate Task-Specific Adapters from Task Description.
Improving Compositional Generalization in Classification Tasks via Structure Annotations.
Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event.
Towards more equitable question answering systems: How much more data do you need?
Cross-lingual Text Classification with Heterogeneous Graph Neural Network.
The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes.
Don't Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models.
Beyond Laurel/Yanny: An Autoencoder-Enabled Search for Polyperceivable Audio.
Unsupervised Enrichment of Persona-grounded Dialog with Background Stories.
A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space.
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking.
A Mixture-of-Experts Model for Antonym-Synonym Discrimination.
More than Text: Multi-modal Chinese Word Segmentation.
When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation.
Improving Arabic Diacritization with Regularized Decoding and Adversarial Training.
TIMERS: Document-level Temporal Relation Extraction.
Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking.
Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation.
Towards Generative Aspect-Based Sentiment Analysis.
Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis.
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer.
Zero-shot Fact Verification by Claim Generation.
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering.
OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres.
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter.
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints.
Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models.
An Exploratory Analysis of Multilingual Word-Level Quality Estimation with Cross-Lingual Transformers.
AligNarr: Aligning Narratives on Movies.
Discrete Cosine Transform as Universal Sentence Encoder.
DefSent: Sentence Embeddings using Definition Sentences.
Exploring Listwise Evidence Reasoning with T5 for Fact Verification.
Happy Dance, Slow Clap: Using Reaction GIFs to Predict Induced Affect on Twitter.
Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning.
On Orthogonality Constraints for Transformers.
Adaptive Nearest Neighbor Machine Translation.
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation.
Men Are Elected, Women Are Married: Events Gender Bias on Wikipedia.
Quantifying and Avoiding Unfair Qualification Labour in Crowdsourcing.
Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models.
Zero-shot Event Extraction via Transfer Learning: Challenges and Insights.
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction.
PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation.
On Positivity Bias in Negative Reviews.
eMLM: A New Pre-training Objective for Emotion Related Tasks.
MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network.
Enhancing Descriptive Image Captioning with Natural Language Inference.
Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation.
A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering.
Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards.
Higher-order Derivatives of Weighted Finite-state Machines.
Multilingual Agreement for Multilingual Neural Machine Translation.
Anchor-based Bilingual Word Embeddings for Low-Resource Languages.
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning.
WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation.
How effective is BERT without word ordering? Implications for language understanding and data privacy.
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification.
Continual Quality Estimation with Online Bayesian Meta-Learning.
What's in the Box? An Analysis of Undesirable Content in the Common Crawl Corpus.
An Improved Model for Voicing Silent Speech.
Enforcing Consistency in Weakly Supervised Semantic Parsing.
AND does not mean OR: Using Formal Languages to Study Language Models' Representations.
Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models.
Relative Importance in Sentence Processing.
The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models.
Is Sparse Attention more Interpretable?
Machine Translation into Low-resource Language Varieties.
Gender bias amplification during Speed-Quality optimization in Neural Machine Translation.
N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses.
Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries.
Automatic Fake News Detection: Are Models Learning to Reason?
How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation?
Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions.
Video Paragraph Captioning as a Text Summarization Task.
Attention Flows are Shapley Value Explanations.
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer.
Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition.
Difficulty-Aware Machine Translation Evaluation.
Enhancing Entity Boundary Detection for Better Chinese Named Entity Recognition.
Coreference Resolution without Span Representations.
On Training Instance Selection for Few-Shot Neural Text Generation.
Catchphrase: Automatic Detection of Cultural References.
Frontmatter.
