emnlp56

emnlp 2021 论文列表

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021.

Detecting Contact-Induced Semantic Shifts: What Can Embedding-Based Methods Do in Practice?

电商所评分:4

Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration.

电商所评分:7

Semi-Supervised Exaggeration Detection of Health Science Press Releases.

电商所评分:10

GeneSis: A Generative Approach to Substitutes in Context.

电商所评分:7

Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization.

电商所评分:8

VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment.

电商所评分:8

Is Everything in Order? A Simple Way to Order Sentences.

电商所评分:10

Multivalent Entailment Graphs for Question Answering.

电商所评分:4

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning.

电商所评分:6

Softmax Tree: An Accurate, Fast Classifier When the Number of Classes Is Large.

电商所评分:5

MTAdam: Automatic Balancing of Multiple Training Loss Terms.

电商所评分:5

Self-training with Few-shot Rationalization.

电商所评分:1

Types of Out-of-Distribution Texts and How to Detect Them.

电商所评分:6

Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features.

电商所评分:6

IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization.

电商所评分:1

Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression.

电商所评分:10

How to Train BERT with an Academic Budget.

电商所评分:6

Finetuning Pretrained Transformers into RNNs.

电商所评分:3

Block Pruning For Faster Transformers.

电商所评分:6

PermuteFormer: Efficient Relative Position Encoding for Long Sequences.

电商所评分:4

What to Pre-Train on? Efficient Intermediate Task Selection.

电商所评分:5

A New Representation for Span-based CCG Parsing.

电商所评分:7

Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering.

电商所评分:9

Efficient Sampling of Dependency Structure.

电商所评分:6

A Root of a Problem: Optimizing Single-Root Dependency Parsing.

电商所评分:7

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement.

电商所评分:9

IndoNLI: A Natural Language Inference Dataset for Indonesian.

电商所评分:7

Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing.

电商所评分:1

Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema.

电商所评分:7

Visually Grounded Reasoning across Languages and Cultures.

电商所评分:8

Automatic Text Evaluation through the Lens of Wasserstein Barycenters.

电商所评分:7

Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction.

电商所评分:2

Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction.

电商所评分:1

XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment.

电商所评分:1

Few-Shot Named Entity Recognition: An Empirical Baseline Study.

电商所评分:1

HittER: Hierarchical Transformers for Knowledge Graph Embeddings.

电商所评分:7

Open Knowledge Graphs Canonicalization using Variational Autoencoders.

电商所评分:5

Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training.

电商所评分:3

Studying word order through iterative shuffling.

电商所评分:1

FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging.

电商所评分:2

Rationales for Sequential Predictions.

电商所评分:6

Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords.

电商所评分:2

Discretized Integrated Gradients for Explaining Language Models.

电商所评分:1

Measuring Association Between Labels and Free-Text Rationales.

电商所评分:5

Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias.

电商所评分:7

XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation.

电商所评分:10

Neural Machine Translation Quality and Post-Editing Performance.

电商所评分:1

UNKs Everywhere: Adapting Multilingual Language Models to New Scripts.

电商所评分:8

Investigating the Helpfulness of Word-Level Quality Estimation for Post-Editing Machine Translation Output.

电商所评分:7

AUTOSUMM: Automatic Model Creation for Text Summarization.

电商所评分:2

MassiveSumm: a very large-scale, very multilingual, news summarisation dataset.

电商所评分:7

Chinese Opinion Role Labeling with Corpus Translation: A Pivot Study.

电商所评分:1

On Classifying whether Two Texts are on the Same Side of an Argument.

电商所评分:6

The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learning.

电商所评分:6

An Information-Theoretic Characterization of Morphological Fusion.

电商所评分:5

A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders.

电商所评分:3

PAUSE: Positive and Annealed Unlabeled Sentence Embedding.

电商所评分:10

"Was it "stated" or was it "claimed"?: How linguistic bias affects generative language models.

电商所评分:8

"So You Think You're Funny?": Rating the Humour Quotient in Standup Comedy.

电商所评分:5

SWEAT: Scoring Polarization of Topics across Different Corpora.

电商所评分:4

Learning Bill Similarity with Annotated and Augmented Corpora of Bills.

电商所评分:2

Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks.

电商所评分:2

Assessing the Reliability of Word Embedding Gender Bias Measures.

电商所评分:5

Measuring Sentence-Level and Aspect-Level (Un)certainty in Science Communications.

电商所评分:8

Identifying Morality Frames in Political Tweets using Relational Learning.

电商所评分:1

Using Sociolinguistic Variables to Reveal Changing Attitudes Towards Sexuality and Gender.

电商所评分:10

Guilt by Association: Emotion Intensities in Lexical Representations.

电商所评分:5

Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings.

电商所评分:6

PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models.

电商所评分:1

QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions.

电商所评分:1

Integrating Deep Event-Level and Script-Level Information for Script Event Prediction.

电商所评分:7

HypMix: Hyperbolic Interpolative Data Augmentation.

电商所评分:1

Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers.

电商所评分:3

COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real Images.

电商所评分:5

On Pursuit of Designing Multi-modal Transformer for Video Grounding.

电商所评分:7

Inflate and Shrink: Enriching and Reducing Interactions for Fast Text-Image Retrieval.

电商所评分:2

Jointly Learning to Repair Code and Generate Commit Message.

电商所评分:2

Wasserstein Selective Transfer Learning for Cross-domain Text Mining.

电商所评分:5

UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph Inference.

电商所评分:6

Meta Distant Transfer Learning for Pre-trained Language Models.

电商所评分:8

A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis.

电商所评分:8

Exploring Methods for Generating Feedback Comments for Writing Learning.

电商所评分:4

A Relation-Oriented Clustering Method for Open Relation Extraction.

电商所评分:4

Maximal Clique Based Non-Autoregressive Open Information Extraction.

电商所评分:6

Uncovering Main Causalities for Long-tailed Information Extraction.

电商所评分:1

Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion.

电商所评分:7

Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction.

电商所评分:7

Set Generation Networks for End-to-End Knowledge Base Population.

电商所评分:9

Numerical reasoning in machine reading comprehension tasks: are we there yet?

电商所评分:6

Evaluation Paradigms in Question Answering.

电商所评分:1

What's in a Name? Answer Equivalence For Open-Domain Question Answering.

电商所评分:5

Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation.

电商所评分:2

Case-based Reasoning for Natural Language Queries over Knowledge Bases.

电商所评分:8

Contrastive Domain Adaptation for Question Answering using Limited Text Corpora.

电商所评分:9

Value-aware Approximate Attention.

电商所评分:5

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks.

电商所评分:6

KnowMAN: Weakly Supervised Multinomial Adversarial Networks.

电商所评分:4

Knowledge Graph Representation Learning using Ordinary Differential Equations.

电商所评分:5

Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning.

电商所评分:7

Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP.

电商所评分:4

Neuralizing Regular Expressions for Slot Filling.

电商所评分:10

Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling.

电商所评分:6

Revisiting Tri-training of Dependency Parsers.

电商所评分:9

Enriching and Controlling Global Semantics for Text Summarization.

电商所评分:4

Learning Opinion Summarizers by Selecting Informative Reviews.

电商所评分:9

Models and Datasets for Cross-Lingual Summarisation.

电商所评分:4

ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization.

电商所评分:7

BARThez: a Skilled Pretrained French Sequence-to-Sequence Model.

电商所评分:4

Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems.

电商所评分:8

Caption Enriched Samples for Improving Hateful Memes Detection.

电商所评分:2

A Unified Speaker Adaptation Approach for ASR.

电商所评分:7

Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy.

电商所评分:7

R\^3Net: Relation-embedded Representation Reconstruction Network for Change Captioning.

电商所评分:3

Language Models are Few-Shot Butlers.

电商所评分:9

Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding.

电商所评分:3

Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos.

电商所评分:2

PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction.

电商所评分:3

Exploring Non-Autoregressive Text Style Transfer.

电商所评分:4

Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer.

电商所评分:7

Towards Label-Agnostic Emotion Embeddings.

电商所评分:10

Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching.

电商所评分:1

Aspect Sentiment Quad Prediction as Paraphrase Generation.

电商所评分:8

Does Social Pressure Drive Persuasion in Online Fora?

电商所评分:6

BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification.

电商所评分:1

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis.

电商所评分:3

An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction.

电商所评分:10

YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews.

电商所评分:3

Unimodal and Crossmodal Refinement Network for Multimodal Sequence Fusion.

电商所评分:5

Bridging Perception, Memory, and Inference through Semantic Relations.

电商所评分:3

Revisiting Self-training for Few-shot Learning of Language Model.

电商所评分:9

NB-MLM: Efficient Domain Adaptation of Masked Language Models for Sentiment Analysis.

电商所评分:1

Cross-lingual Sentence Embedding using Multi-Task Learning.

电商所评分:8

Integrating Personalized PageRank into Neural Word Sense Disambiguation.

电商所评分:3

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing.

电商所评分:5

Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning.

电商所评分:4

Distilling Relation Embeddings from Pretrained Language Models.

电商所评分:5

Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification.

电商所评分:6

Cross-Domain Label-Adaptive Stance Detection.

电商所评分:9

Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs.

电商所评分:4

SPARQLing Database Queries from Intermediate Question Decompositions.

电商所评分:3

Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing.

电商所评分:6

Enhancing the Context Representation in Similarity-based Word Sense Disambiguation.

电商所评分:6

Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset.

电商所评分:8

NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender Neutral Alternatives.

电商所评分:8

What happens if you treat ordinal ratings as interval data? Human evaluations in NLP are even more under-powered than you think.

电商所评分:4

Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization.

电商所评分:10

Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors.

电商所评分:9

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability.

电商所评分:8

IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation.

电商所评分:4

MLEC-QA: A Chinese Multi-Choice Biomedical Question Answering Dataset.

电商所评分:2

BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief.

电商所评分:2

Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation.

电商所评分:9

Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs.

电商所评分:10

Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection.

电商所评分:1

English Machine Reading Comprehension Datasets: A Survey.

电商所评分:1

Finnish Dialect Identification: The Effect of Audio and Text.

电商所评分:5

ClauseRec: A Clause Recommendation Framework for AI-aided Contract Authoring.

电商所评分:7

Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case.

电商所评分:10

To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning.

电商所评分:8

Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models.

电商所评分:3

Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems.

电商所评分:2

Detect and Classify - Joint Span Detection and Classification for Health Outcomes.

电商所评分:6

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation.

电商所评分:2

Preventing Author Profiling through Zero-Shot Multilingual Back-Translation.

电商所评分:8

STaCK: Sentence Ordering with Temporal Commonsense Knowledge.

电商所评分:6

BERT-Beta: A Proactive Probabilistic Approach to Text Moderation.

电商所评分:3

Parallel Refinements for Lexically Constrained Text Generation with BART.

电商所评分:3

Unsupervised Multi-View Post-OCR Error Correction With Language Models.

电商所评分:4

Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification.

电商所评分:10

Cross-Policy Compliance Detection via Question Answering.

电商所评分:7

Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation.

电商所评分:8

Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification.

电商所评分:1

Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages.

电商所评分:8

Efficient Inference for Multilingual Neural Machine Translation.

电商所评分:3

Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models.

电商所评分:6

Discrete and Soft Prompting for Multilingual Models.

电商所评分:5

One Source, Two Targets: Challenges and Rewards of Dual Decoding.

电商所评分:7

Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution.

电商所评分:3

Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach.

电商所评分:1

Effective Fine-Tuning Methods for Cross-lingual Adaptation.

电商所评分:4

Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT.

电商所评分:7

Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation.

电商所评分:4

Graph Algorithms for Multiparallel Word Alignment.

电商所评分:10

An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation.

电商所评分:5

Document Graph for Neural Machine Translation.

电商所评分:2

Machine Translation Decoding beyond Beam Search.

电商所评分:2

A Strong Baseline for Query Efficient Attacks in a Black Box Setting.

电商所评分:5

FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations.

电商所评分:8

RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models.

电商所评分:10

Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs.

电商所评分:4

BiQUE: Biquaternionic Embeddings of Knowledge Graphs.

电商所评分:6

Code-switched inspired losses for spoken dialog representations.

电商所评分:3

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting.

电商所评分:2

Synthetic Textual Features for the Large-Scale Detection of Basic-level Categories in English and Mandarin.

电商所评分:6

On Homophony and Rényi Entropy.

电商所评分:2

Is Information Density Uniform in Task-Oriented Dialogues?

电商所评分:4

Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification.

电商所评分:3

Sequence Length is a Domain: Length-based Overfitting in Transformer Models.

电商所评分:10

Locke's Holiday: Belief Bias in Machine Reading.

电商所评分:3

Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods.

电商所评分:9

Don't Search for a Search Method - Simple Heuristics Suffice for Adversarial Text Attacks.

电商所评分:8

What's in Your Head? Emergent Behaviour in Multi-Task Transformer Models.

电商所评分:6

Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience.

电商所评分:7

Bayesian Topic Regression for Causal Inference.

电商所评分:10

Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution.

电商所评分:1

Deep Attention Diffusion Graph Neural Networks for Text Classification.

电商所评分:4

Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement.

电商所评分:10

Matching-oriented Embedding Quantization For Ad-hoc Retrieval.

电商所评分:6

Time-dependent Entity Embedding is not All You Need: A Re-evaluation of Temporal Knowledge Graph Completion Models under a Unified Framework.

电商所评分:3

Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction.

电商所评分:5

Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention.

电商所评分:7

Extracting Event Temporal Relations via Hyperbolic Geometry.

电商所评分:1

TDEER: An Efficient Translating Decoding Schema for Joint Extraction of Entities and Relations.

电商所评分:8

Low-Rank Subspaces for Unsupervised Entity Linking.

电商所评分:3

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation.

电商所评分:3

Paraphrasing Compound Nominalizations.

电商所评分:7

A Bag of Tricks for Dialogue Summarization.

电商所评分:3

Document-Level Text Simplification: Dataset, Criteria and Baseline.

电商所评分:3

Text Detoxification using Large Pre-trained Neural Models.

电商所评分:4

CAPE: Context-Aware Private Embeddings for Private Language Learning.

电商所评分:1

Understanding and Overcoming the Challenges of Efficient Transformer Quantization.

电商所评分:4

AdapterDrop: On the Efficiency of Adapters in Transformers.

电商所评分:9

A Semantic Filter Based on Relations for Knowledge Graph Completion.

电商所评分:4

Dynamic Forecasting of Conversation Derailment.

电商所评分:4

Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance.

电商所评分:5

Zero-Shot Dialogue State Tracking via Cross-Task Transfer.

电商所评分:6

A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition.

电商所评分:6

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking.

电商所评分:7

$Q^2$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering.

电商所评分:6

Proxy Indicators for the Quality of Open-domain Dialogues.

电商所评分:2

Learning Neural Templates for Recommender Dialogue System.

电商所评分:1

#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention.

电商所评分:7

Come hither or go away? Recognising pre-electoral coalition signals in the news.

电商所评分:2

Point-of-Interest Type Prediction using Text and Images.

电商所评分:7

Classifying Dyads for Militarized Conflict Analysis.

电商所评分:1

Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity Estimation.

电商所评分:9

LM-Critic: Language Models for Unsupervised Grammatical Error Correction.

电商所评分:4

Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories.

电商所评分:1

ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning.

电商所评分:10

Constrained Language Models Yield Few-Shot Semantic Parsers.

电商所评分:1

Controllable Semantic Parsing via Retrieval Augmentation.

电商所评分:1

A Secure and Efficient Federated Learning Framework for NLP.

电商所评分:8

Word-Level Coreference Resolution.

电商所评分:6

Highly Parallel Autoregressive Entity Linking with Discriminative Correction.

电商所评分:7

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation.

电商所评分:6

When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute.

电商所评分:4

Learning with Different Amounts of Annotation: From Zero to Many Labels.

电商所评分:8

MATE: Multi-view Attention for Table Transformer Efficiency.

电商所评分:2

Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation.

电商所评分:8

RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms.

电商所评分:6

ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations.

电商所评分:7

On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings.

电商所评分:3

CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

电商所评分:3

MS\^2: Multi-Document Summarization of Medical Studies.

电商所评分:10

Effective Sequence-to-Sequence Dialogue State Tracking.

电商所评分:9

Investigating Robustness of Dialog Models to Popular Figurative Language Constructs.

电商所评分:1

Multilingual and Cross-Lingual Intent Detection from Spoken Data.

电商所评分:5

Continual Learning in Task-Oriented Dialogue Systems.

电商所评分:5

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach.

电商所评分:9

Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules.

电商所评分:10

ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Detection in Conversational AI.

电商所评分:3

SituatedQA: Incorporating Extra-Linguistic Contexts into QA.

电商所评分:8

Explaining Answers with Entailment Trees.

电商所评分:9

Learning with Instance Bundles for Reading Comprehension.

电商所评分:3

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering.

电商所评分:4

How much coffee was consumed during EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI.

电商所评分:6

Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy.

电商所评分:2

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training.

电商所评分:1

Learning Kernel-Smoothed Machine Translation with Retrieved Examples.

电商所评分:7

Improving Multilingual Translation by Representation and Gradient Regularization.

电商所评分:7

Don't Go Far Off: An Empirical Study on Neural Poetry Translation.

电商所评分:9

Robust Open-Vocabulary Translation from Visual Text Representations.

电商所评分:3

Perturbation CheckLists for Evaluating NLG Evaluation Metrics.

电商所评分:9

ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries.

电商所评分:3

On the Influence of Masking Policies in Intermediate Pre-training.

电商所评分:9

CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP.

电商所评分:10

AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples.

电商所评分:10

Evaluating the Morphosyntactic Well-formedness of Generated Texts.

电商所评分:10

Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework.

电商所评分:8

I Wish I Would Have Loved This One, But I Didn't - A Multilingual Dataset for Counterfactual Detection in Product Review.

电商所评分:1

DWUG: A large Resource of Diachronic Word Usage Graphs in Four Languages.

电商所评分:9

Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval.

电商所评分:1

Entity-Based Knowledge Conflicts in Question Answering.

电商所评分:5

Surface Form Competition: Why the Highest Probability Answer Isn't Always Right.

电商所评分:8

Have You Seen That Number? Investigating Extrapolation in Question Answering Models.

电商所评分:5