coling 2020 论文列表
Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020.
|
Neural Language Modeling for Named Entity Recognition.
Augmenting NLP models using Latent Feature Interpolations.
Autoregressive Reasoning over Chains of Facts with Transformers.
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters.
Attention Word Embedding.
Scale down Transformer by Grouping Features for a Lightweight Character-level Language Model.
Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths.
Do Neural Language Models Overcome Reporting Bias?
Exploring the Value of Personalized Word Embeddings.
Neural Unsupervised Domain Adaptation in NLP - A Survey.
Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations.
Learning distributed sentence vectors with bi-directional 3D convolutions.
Embedding Dynamic Attributed Networks by Modeling the Evolution Processes.
Language Model Transformers as Evaluators for Open-domain Dialogues.
German's Next Language Model.
Resource Constrained Dialog Policy Learning Via Differentiable Inductive Logic Programming.
Out-of-Task Training for Dialog State Tracking Models.
Statistical Parsing of Tree Wrapping Grammars.
Incremental Neural Lexical Coherence Modeling.
Tree Representations in Transition System for RST Parsing.
Intrinsic Quality Assessment of Arguments.
Multilingual Neural RST Discourse Parsing.
Improving Document-Level Sentiment Analysis with User and Product Context.
A Sentence Cloze Dataset for Chinese Machine Reading Comprehension.
Fair Evaluation in Concept Normalization: a Large-scale Comparative Analysis for BERT-based Models.
Creation of Corpus and analysis in Code-Mixed Kannada-English Twitter data for Emotion Prediction.
Expert Concept-Modeling Ground Truth Construction for Word Embeddings Evaluation in Concept-Focused Domains.
A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples.
New Benchmark Corpus and Models for Fine-grained Event Classification: To BERT or not to BERT?
DaN+: Danish Nested Named Entities and Lexical Normalization.
Exploring the Language of Data.
RoBERT - A Romanian BERT Model.
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps.
Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus.
Domain-Specific Sentiment Lexicons Induced from Labeled Documents.
Biomedical Concept Relatedness - A large EHR-based benchmark.
Human or Neural Translation?
XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection.
Continual Lifelong Learning in Natural Language Processing: A Survey.
SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction.
NYTWIT: A Dataset of Novel Words in the New York Times.
Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs.
Read and Reason with MuSeRC and RuCoS: Datasets for Machine Reading Comprehension for Russian.
DT-QDC: A Dataset for Question Comprehension in Online Test.
FASTMATCH: Accelerating the Inference of BERT-based Text Matching.
Multi-choice Relational Reasoning for Machine Reading Comprehension.
Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction.
Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction.
Dual Supervision Framework for Relation Extraction with Distant Supervision and Human Annotation.
Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction.
Regularized Attentive Capsule Network for Overlapped Relation Extraction.
Modeling Evolution of Message Interaction for Rumor Resolution.
Detect All Abuse! Toward Universal Abusive Language Detection Models.
XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages.
Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News.
HateGAN: Adversarial Generative-Based Data Augmentation for Hate Speech Detection.
Context in Informational Bias Detection.
Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation.
Mama/Papa, Is this Text for Me?
A Survey of Automatic Personality Detection from Texts.
AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts.
Mining Crowdsourcing Problems from Discussion Forums of Workers.
Are We Ready for this Disaster? Towards Location Mention Recognition from Crisis Tweets.
Hierarchical Text Segmentation for Medieval Manuscripts.
A Deep Metric Learning Method for Biomedical Passage Retrieval.
"What is on your mind?" Automated Scoring of Mindreading in Childhood and Early Adolescence.
Explainable and Sparse Representations of Academic Articles for Knowledge Exploration.
Aspect-based Document Similarity for Research Papers.
Pointing to Select: A Fast Pointer-LSTM for Long Text Classification.
Multilingual Epidemiological Text Classification: A Comparative Study.
Text Classification by Contrastive Learning and Cross-lingual Data Augmentation for Alzheimer's Disease Detection.
Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification.
Fact vs. Opinion: the Role of Argumentation Features in News Classification.
How coherent are neural models of coherence?
Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution.
Fine-grained Information Status Classification Using Discourse Context-Aware BERT.
A Straightforward Approach to Narratologically Grounded Character Identification.
Neural Automated Essay Scoring Incorporating Handcrafted Features.
Analysing cross-lingual transfer in lemmatisation for Indian languages.
Building The First English-Brazilian Portuguese Corpus for Automatic Post-Editing.
Understanding Translationese in Multi-view Embedding Spaces.
Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction.
The SADID Evaluation Datasets for Low-Resource Spoken Language Machine Translation of Arabic Dialects.
Rethinking the Value of Transformer Components.
A Locally Linear Procedure for Word Translation.
Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora.
A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction.
Better Sign Language Translation with STMC-Transformer.
The Transference Architecture for Automatic Post-Editing.
WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking.
Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models.
PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents.
A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment.
100, 000 Podcasts: A Spoken English Document Corpus.
Don't Patronize Me! An Annotated Dataset with Patronizing and Condescending Language towards Vulnerable Communities.
Cross-Lingual Emotion Lexicon Induction using Representation Alignment in Low-Resource Settings.
The Indigenous Languages Technology project at NRC Canada: An empowerment-oriented approach to developing language software.
An Analysis of Dataset Overlap on Winograd-Style Tasks.
Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers.
Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework.
Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches.
Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification.
Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training.
Towards automatically generating Questions under Discussion to link information and discourse structure.
Variation in Coreference Strategies across Genres and Production Media.
A Neural Model for Aggregating Coreference Annotation in Crowdsourcing.
Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading.
Exploiting a lexical resource for discourse connective disambiguation in German.
TWEETSUM: Event oriented Social Summarization Dataset.
SumTitles: a Summarization Dataset with Low Extractiveness.
On the Faithfulness for E-commerce Product Summarization.
Metrics also Disagree in the Low Scoring Range: Revisiting Summarization Evaluation Metrics.
An Anchor-Based Automatic Evaluation Metric for Document Summarization.
How Domain Terminology Affects Meeting Summarization Performance.
HOLMS: Alternative Summary Evaluation with Large Language Models.
Controllable Abstractive Sentence Summarization with Guiding Entities.
Multimodal Sentence Summarization via Multimodal Selective Encoding.
WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization.
Flight of the PEGASUS? Comparing Transformers on Few-shot and Zero-shot Multi-document Abstractive Summarization.
Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT.
At Which Level Should We Extract? An Empirical Analysis on Extractive Document Summarization.
Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization.
IntKB: A Verifiable Interactive Framework for Knowledge Base Completion.
Knowledge Base Embedding By Cooperative Knowledge Distillation.
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification.
Embedding Meta-Textual Information for Improved Learning to Rank.
ManyEnt: A Dataset for Few-shot Entity Typing.
Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network.
Word-Level Uncertainty Estimation for Black-Box Text Classifiers using RNNs.
Exploiting Narrative Context and A Priori Knowledge of Categories in Textual Emotion Classification.
Unsupervised Fine-tuning for Text Clustering.
Go Simple and Pre-Train on Domain-Specific Corpora: On the Role of Training Data for Text Classification.
KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi.
Data Augmentation for Multiclass Utterance Classification - A Systematic Study.
Argumentation Mining on Essays at Multi Scales.
Words are the Window to the Soul: Language-based User Representations for Fake News Detection.
Debunking Rumors on Twitter with Tree Transformer.
Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning.
Explainable Automated Fact-Checking: A Survey.
Exploiting Microblog Conversation Structures to Detect Rumors.
Scientific Keyphrase Identification and Classification by Pre-Trained Language Models Intermediate Task Transfer Learning.
Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations.
News Editorials: Towards Summarizing Long Argumentative Texts.
SaSAKE: Syntax and Semantics Aware Keyphrase Extraction from Research Papers.
Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks.
CosMo: Conditional Seq2Seq-based Mixture Model for Zero-Shot Commonsense Question Answering.
Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification.
An empirical analysis of existing systems and datasets toward general simple question answering.
Diverse and Non-redundant Answer Set Extraction on Community QA based on DPPs.
User Memory Reasoning for Conversational Recommendation.
Diverse Keyphrase Generation with Neural Unlikelihood Training.
Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction.
Identifying Motion Entities in Natural Language and A Case Study for Named Entity Recognition.
Hy-NLI: a Hybrid system for Natural Language Inference.
Auto-Encoding Variational Bayes for Inferring Topics and Visualization.
A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection.
Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering.
Intra-Correlation Encoding for Chinese Sentence Intention Matching.
Pick a Fight or Bite your Tongue: Investigation of Gender Differences in Idiomatic Language Usage.
Distinguishing Between Foreground and Background Events in News.
Answer-driven Deep Question Generation based on Reinforcement Learning.
Priorless Recurrent Networks Learn Curiously.
Classifier Probes May Just Learn from Linear Context Features.
A Mixture-of-Experts Model for Learning Multi-Facet Entity Embeddings.
Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks.
AraBench: Benchmarking Dialectal Arabic-English Machine Translation.
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations.
TransQuest: Translation Quality Estimation with Cross-lingual Transformers.
Informative Manual Evaluation of Machine Translation Output.
Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English.
Inconsistencies in Crowdsourced Slot-Filling Annotations: A Typology and Identification Methods.
Adversarial Learning on the Latent Space for Diverse Dialog Generation.
Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System.
Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions.
Few-shot Pseudo-Labeling for Intent Detection.
Intra-/Inter-Interaction Network with Latent Interaction Modeling for Multi-turn Response Selection.
A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations.
An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution.
Understanding Unnatural Questions Improves Reasoning over Text.
Reasoning Requirements for Indirect Speech Act Interpretation.
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling.
Two-level classification for dialogue act recognition in task-oriented dialogues.
A Multitask Active Learning Framework for Natural Language Understanding.
A Taxonomy of Empathetic Response Intents in Human Social Conversations.
Inflating Topic Relevance with Ideology: A Case Study of Political Ideology Bias in Social Topic Detection Models.
Measuring Correlation-to-Causation Exaggeration in Press Releases.
GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion.
Predicting Clickbait Strength in Online Social Media.
Hierarchical Trivia Fact Extraction from Wikipedia Articles.
Manual Clustering and Spatial Arrangement of Verbs for Multilingual Evaluation and Typology Analysis.
Would you describe a leopard as yellow? Evaluating crowd-annotations with justified and informative disagreement.
Identifying Annotator Bias: A new IRT-based method for bias identification.
A Human Evaluation of AMR-to-English Generation Systems.
CLUE: A Chinese Language Understanding Evaluation Benchmark.
SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP.
ContraCAT: Contrastive Coreference Analytical Templates for Machine Translation.
Emergent Communication Pretraining for Few-Shot Machine Translation.
Cross-lingual Transfer Learning for Grammatical Error Correction.
Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages.
Wiktionary Normalization of Translations and Morphological Information.
Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models.
Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities.
Revitalization of Indigenous Languages through Pre-processing and Neural Machine Translation: The case of Inuktitut.
Morphological disambiguation from stemming data.
Incorporating Inner-word and Out-word Features for Mongolian Morphological Segmentation.
Syllable-based Neural Thai Word Segmentation.
Joint Persian Word Segmentation Correction and Zero-Width Non-Joiner Recognition Using BERT.
Interactive Word Completion for Morphologically Complex Languages.
Coreference information guides human expectations during natural reading.
A Linguistic Perspective on Reference: Choosing a Feature Set for Generating Referring Expressions in Context.
Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing.
Aspectuality Across Genre: A Distributional Semantics Approach.
Living Machines: A study of atypical animacy.
Domain Transfer based Data Augmentation for Neural Query Translation.
Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation.
Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity.
Effective Use of Target-side Context for Neural Machine Translation.
Leveraging Discourse Rewards for Document-Level Neural Machine Translation.
EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation.
MEISD: A Multimodal Multi-Label Emotion, Intensity and Sentiment Dialogue Dataset for Emotion Recognition and Sentiment Analysis in Conversations.
Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer.
Combining Cognitive Modeling and Reinforcement Learning for Clarification in Dialogue.
Does Gender Matter? Towards Fairness in Dialogue Systems.
Context-Aware Cross-Attention for Non-Autoregressive Translation.
A Document-Level Neural Machine Translation Model with Dynamic Caching Guided by Theme-Rheme Information.
Neural Transduction for Multilingual Lexical Translation.
Unifying Input and Output Smoothing in Neural Machine Translation.
Intermediate Self-supervised Learning for Machine Translation Quality Estimation.
Lost in Back-Translation: Emotion Preservation in Neural Machine Translation.
Filtering Back-Translated Data in Unsupervised Neural Machine Translation.
The Two Shades of Dubbing in Neural Machine Translation.
Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation.
Supervised Visual Attention for Multimodal Neural Machine Translation.
Token Drop mechanism for Neural Machine Translation.
Bilingual Subword Segmentation for Neural Machine Translation.
Layer-Wise Multi-View Learning for Neural Machine Translation.
Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation.
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English.
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training.
A Two-Level Interpretation of Modality in Human-Robot Dialogue.
Integrating User History into Heterogeneous Graph for Dialogue Act Recognition.
A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection.
HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations.
Suggest me a movie for tonight: Leveraging Knowledge Graphs for Conversational Recommendation.
Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems.
Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition.
Intent Mining from past conversations for Conversational Agent.
Towards Topic-Guided Conversational Recommender System.
Diverse dialogue generation with context dependent dynamic loss function.
Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling.
Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems.
PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation.
An Iterative Emotion Interaction Network for Emotion Recognition in Conversations.
Topic-relevant Response Generation using Optimal Transport for an Open-domain Dialog System.
When and Who? Conversation Transition Based on Bot-Agent Symbiosis Learning Network.
Corpus-based Identification of Verbs Participating in Verb Alternations Using Classification and Manual Annotation.
How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text.
CxGBERT: BERT meets Construction Grammar.
Comparative Probing of Lexical Semantics Theories for Cognitive Plausibility and Technological Usefulness.
Real-Valued Logics for Typological Universals: Framework and Application.
Dynamic Curriculum Learning for Low-Resource Neural Machine Translation.
Neural Machine Translation Models with Back-Translation for the Extremely Low-Resource Indigenous Language Bribri.
Breeding Gender-aware Direct Speech Translation Systems.
Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation.
Integrating Domain Terminology into Neural Machine Translation.
Second-Order Unsupervised Neural Dependency Parsing.
Learning from Non-Binary Constituency Trees via Tensor Decomposition.
Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers.
Semi-supervised Autoencoding Projective Dependency Parsing.
An Analysis of Simple Data Augmentation for Named Entity Recognition.
How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention.
Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction.
Porous Lattice Transformer Encoder for Chinese NER.
Data Augmentation via Subtree Swapping for Dependency Parsing of Low-Resource Languages.
Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations.
Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining.
A Unifying Theory of Transition-based and Sequence Labeling Parsing.
Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levels.
Evaluating Pretrained Transformer-based Models on the Task of Fine-Grained Named Entity Recognition.
What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language.
An analysis of language models for metaphor recognition.
Bridging Resolution: A Survey of the State of the Art.
Target Word Masking for Location Metonymy Resolution.
Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension.
Invertible Tree Embeddings using a Cryptographic Role Embedding Scheme.
CoLAKE: Contextualized Language and Knowledge Embedding.
The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks.
Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis.
Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention.
Cross-Lingual Document Retrieval with Smooth Learning.
Deep Inside-outside Recursive Autoencoder with All-span Objective.
Specializing Word Vectors by Spectral Decomposition on Heterogeneously Twisted Graphs.
Rethinking Skip Connection with Layer Normalization.
Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings.
Distill and Replay for Continual Language Learning.
Automatic Discovery of Heterogeneous Machine Learning Pipelines: An Application to Natural Language Processing.
Improving Human-Labeled Data through Dynamic Automatic Conflict Resolution.
Multitask Learning-Based Neural Bridging Reference Resolution.
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation.
Decolonising Speech and Language Technology.
A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI.
Attentively Embracing Noise for Robust Latent Representation in BERT.
Federated Learning for Spoken Language Understanding.
Using Bilingual Patents for Translation Training.
Towards the First Machine Translation System for Sumerian Transliterations.
Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models.
Handling Anomalies of Synthetic Questions in Unsupervised Question Answering.
Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks.
Optimizing Transformer for Low-Resource Neural Machine Translation.
Enabling Interactive Transcription in an Indigenous Community.
Collective Wisdom: Improving Low-resource Neural Machine Translation using Adaptive Knowledge Distillation.
Manifold Learning-based Word Representation Refinement Incorporating Global and Local Information.
Sentence Analogies: Linguistic Regularities in Sentence Embeddings.
An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings.
SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings.
An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification.
Verbal Multiword Expression Identification: Do We Need a Sledgehammer to Crack a Nut?
Homonym normalisation by word sense clustering: a case in Japanese.
Temporal Relations Annotation and Extrapolation Based on Semi-intervals and Boundig Relations.
Sentence Matching with Syntax- and Semantics-Aware BERT.
What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation.
Conception: Multilingually-Enhanced, Human-Readable Concept Vector Representations.
Transformation of Dense and Sparse Text Representations.
Multi-level Alignment Pretraining for Multi-lingual Semantic Parsing.
Emotion Classification by Jointly Learning to Lexiconize and Classify.
LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression.
RANCC: Rationalizing Neural Networks via Concept Clustering.
Task-Aware Representation of Sentences for Generic Text Classification.
Dual Attention Network for Cross-lingual Entity Alignment.
Dual Attention Model for Citation Recommendation.
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition.
Bridge the Gap: High-level Semantic Planning for Image Captioning.
Geo-Aware Image Caption Generation.
Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning.
Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering.
VICTR: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks.
Studying Taxonomy Enrichment on Diachronic WordNet Versions.
Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings.
QANom: Question-Answer driven SRL for Nominalizations.
Definition Frames: Using Definitions for Hybrid Concept Representations.
Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments.
Coordination Boundary Identification without Labeled Data for Compound Terms Disambiguation.
Modality Enriched Neural Network for Metaphor Detection.
When Beards Start Shaving Men: A Subject-object Resolution Test Suite for Morpho-syntactic and Semantic Model Introspection.
Leveraging WordNet Paths for Neural Hypernym Prediction.
Normalizing Compositional Structures Across Graphbanks.
Semantic Role Labeling with Heterogeneous Syntactic Knowledge.
Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification.
Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics.
End to End Chinese Lexical Fusion Recognition with Sememe Knowledge.
Solving Math Word Problems with Multi-Encoders and Multi-Decoders.
Autoregressive Affective Language Forecasting: A Self-Supervised Task.
A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing.
One Comment from One Perspective: An Effective Strategy for Enhancing Automatic Music Comment.
Computational Modeling of Affixoid Behavior in Chinese Morphology.
Analogy Models for Neural Word Inflection.
Morphologically Aware Word-Level Translation.
Noise Isn't Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models.
Does Chinese BERT Encode Word Structure?
"Judge me by my size (noun), do you?" YodaLib: A Demographic-Aware Humor Generation Framework.
Generating Instructions at Different Levels of Abstraction.
Adapting a Language Model for Controlled Affective Text Generation.
Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases.
Reinforced Multi-task Approach for Multi-hop Question Generation.
Robust Machine Reading Comprehension by Learning Soft labels.
Conversational Machine Comprehension: a Literature Review.
Syntactic Graph Convolutional Network for Spoken Language Understanding.
Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation Task.
Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation.
To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding?
NUT-RC: Noisy User-generated Text-oriented Reading Comprehension.
ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation.
Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs.
Joint Event Extraction with Hierarchical Policy Network.
Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure.
Incorporating Syntax and Frame Semantics in Neural Network for Machine Reading Comprehension.
Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension.
Bi-directional CognitiveThinking Network for Machine Reading Comprehension.
Improving Spoken Language Understanding by Wisdom of Crowds.
A Vietnamese Dataset for Evaluating Machine Reading Comprehension.
Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources.
Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph.
Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning.
CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering.
Exploring Question-Specific Rewards for Generating Deep Questions.
A Survey of Unsupervised Dependency Parsing.
Context Dependent Semantic Parsing: A Survey.
Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations.
Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding.
Bracketing Encodings for 2-Planar Dependency Parsing.
I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning.
Sentiment Forecasting in Dialog.
A hierarchical approach to vision-based language generation: from simple sentences to complex natural language.
Graph-Based Knowledge Integration for Question Answering over Dialogue.
Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity.
GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation.
Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation.
Dynamic Topic Tracker for KB-to-Text Generation.
MedWriter: Knowledge-Aware Medical Text Generation.
Learning with Contrastive Examples for Data-to-Text Generation.
Story Generation with Rich Details.
Facts2Story: Controlling Text Generation by Key Facts.
Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale.
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning.
Automatic Detection of Machine Generated Text: A Critical Survey.
Retrieval-Augmented Controllable Review Generation.
Topic-driven Ensemble for Online Advertising Generation.
Referring to what you know and do not know: Making Referring Expression Generation Models Generalize To Unseen Entities.
Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication.
Formality Style Transfer with Shared Latent Space.
Ask to Learn: A Study on Curiosity-driven Question Generation.
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer.
Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation.
Heterogeneous Recycle Generation for Chinese Grammatical Error Correction.
Contextualized Embeddings for Enriching Linguistic Analyses on Politeness.
Style versus Content: A distinction without a (learnable) difference?
Automatic Assistance for Academic Word Usage.
Grammatical error detection in transcriptions of spoken English.
A Neural Local Coherence Analysis Model for Clarity Text Scoring.
Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction.
Neural text normalization leveraging similarities of strings and sounds.
How Positive Are You: Text Style Transfer using Adaptive Style Embedding.
Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redaction.
Automatic Distractor Generation for Multiple Choice Questions in Standard Tests.
Taking the Correction Difficulty into Account in Grammatical Error Correction Evaluation.
Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams.
Towards Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning.
Parsers Know Best: German PP Attachment Revisited.
KeyGames: A Game Theoretic Approach to Automatic Keyphrase Extraction.
Multi-grained Chinese Word Segmentation with Weakly Labeled Data.
An Enhanced Knowledge Injection Model for Commonsense Generation.
Generalized Shortest-Paths Encoders for AMR-to-Text Generation.
The ApposCorpus: a new multilingual, multi-domain dataset for factual appositive generation.
TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching.
Mark-Evaluate: Assessing Language Generation using Population Estimation Methods.
CoNAN: A Complementary Neighboring-based Attention Network for Referring Expression Generation.
Image Caption Generation for News Articles.
Offensive Language Detection on Video Live Streaming Chat.
Language-Driven Region Pointer Advancement for Controllable Image Captioning.
Encoding Lexico-Semantic Knowledge using Ensembles of Feature Maps from Deep Convolutional Neural Networks.
Humans Meet Models on Object Naming: A New Dataset and Analysis.
Ad Lingua: Text Classification Improves Symbolism Prediction in Image Advertisements.
Visual-Textual Alignment for Graph Inference in Visual Dialog.
Towards Knowledge-Augmented Visual Question Answering.
RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER.
Reasoning Step-by-Step: Temporal Sentence Localization in Videos via Deep Rectification-Modulation Network.
Personalized Multimodal Feedback Generation in Education.
Connecting the Dots Between Fact Verification and Fake News Detection.
Lin: Unsupervised Extraction of Tasks from Textual Communication.
Detecting de minimis Code-Switching in Historical German Books.
Predicting Personal Opinion on Future Events with Fingerprints.
Medical Knowledge-enriched Textual Entailment Framework.
Modeling Event Salience in Narratives via Barthes' Cardinal Functions.
A Deep Generative Approach to Native Language Identification.
Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction.
Complaint Identification in Social Media with Transformer Networks.
Combining Event Semantics and Degree Semantics for Natural Language Inference.
Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet.
comp-syn: Perceptually Grounded Word Embeddings with Color.
Multi-Task Learning for Knowledge Graph Completion with Pre-trained Language Models.
Vec2Sent: Probing Sentence Embeddings with Natural Language Generation.
Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis.
PoD: Positional Dependency-Based Word Embedding for Aspect Term Extraction.
Autoencoding Improves Pre-trained Word Embeddings.
Improving Relation Extraction with Relational Paraphrase Sentences.
Unsupervised Fact Checking by Counter-Weighted Positive and Negative Evidential Paths in A Knowledge Graph.
ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction.
Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention.
Biased TextRank: Unsupervised Graph-Based Content Extraction.
Document-level Relation Extraction with Dual-tier Heterogeneous Graph.
A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification.
Unsupervised Deep Language and Dialect Identification for Short Texts.
Meta-Information Guided Meta-Learning for Few-Shot Relation Classification.
TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation.
TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking.
Joint Entity and Relation Extraction for Legal Documents with Legal Feature Enhancement.
Graph Enhanced Dual Attention Network for Document-Level Relation Extraction.
KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision.
Knowledge Graph Embedding with Atrous Convolution and Residual Learning.
A Review of Dataset and Labeling Methods for Causality Extraction.
Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification.
Event-Guided Denoising for Multilingual Relation Learning.
Pre-trained Language Model Based Active Learning for Sentence Matching.
On the Practical Ability of Recurrent Neural Networks to Recognize Hierarchical Languages.
Contextual Argument Component Classification for Class Discussions.
DoLFIn: Distributions over Latent Features for Interpretability.
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack.
A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space.
Exploring the zero-shot limit of FewRel.
Multi-Word Lexical Simplification.
AutoMeTS: The Autocomplete for Medical Text Simplification.
On the Helpfulness of Document Context to Sentence Simplification.
Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach.
Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages.
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity.
What Can We Learn from Noun Substitutions in Revision Histories?
Multilingual Irony Detection with Dependency Syntax and Neural Models.
Schema Aware Semantic Reasoning for Interpreting Natural Language Queries in Enterprise Settings.
BERT-based Cohesion Analysis of Japanese Texts.
A BERT-based Dual Embedding Model for Chinese Idiom Prediction.
Lexical Relation Mining in Neural Word Embeddings.
A Retrofitting Model for Incorporating Semantic Relations into Word Embeddings.
Embedding Semantic Taxonomies.
How Relevant Are Selectional Preferences for Transformer-based Language Models?
Word Embedding Binarization with Semantic Information Preservation.
Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution.
Learning Efficient Task-Specific Meta-Embeddings with Word Prisms.
Probing Multilingual BERT for Genetic and Typological Signals.
Improving Word Embeddings through Iterative Refinement of Word- and Character-level Models.
Tiny Word Embeddings Using Globally Informed Reconstruction.
A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation.
Exploring End-to-End Differentiable Natural Logic Modeling.
Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning.
R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning.
Enhancing Neural Models with Vulnerability via Adversarial Attack.
Meet Changes with Constancy: Learning Invariance in Multi-Source Translation.
Situated and Interactive Multimodal Conversations.
Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games.
Multimodal Topic-Enriched Auxiliary Learning for Depression Detection.
SWAFN: Sentimental Words Aware Fusion Network for Multimodal Sentiment Analysis.
Effective Few-Shot Classification with Transfer Learning.
Exploring Amharic Sentiment Analysis from Social Media Texts: Building Annotation Tools and Classification Models.
RuSemShift: a dataset of historical lexical semantic change in Russian.
Context-Aware Text Normalisation for Historical Dialects.
Automatic Charge Identification from Facts: A Few Sentence-Level Charge Annotations is All You Need.
Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages.
Answering Legal Questions by Learning Neural Attentive Text Representation.
Financial Sentiment Analysis: An Investigation into Common Mistakes and Silver Bullets.
A High Precision Pipeline for Financial Knowledge Graph Construction.
Building Large-Scale English and Korean Datasets for Aspect-Level Sentiment Analysis in Automotive Domain.
DocBank: A Benchmark Dataset for Document Layout Analysis.
A Dataset and Evaluation Framework for Complex Geographical Description Parsing.
Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls.
Cross-lingual Annotation Projection in Legal Texts.
Exploring Cross-sentence Contexts for Named Entity Recognition with BERT.
Automated Prediction of Examinee Proficiency from Short-Answer Questions.
Don't take "nswvtnvakgxpm" for an answer -The surprising vulnerability of automatic content scoring systems to adversarial input.
Do Word Embeddings Capture Spelling Variation?
A Corpus for Argumentative Writing Support in German.
Constituency Lattice Encoding for Aspect Term Extraction.
Aspect-Category based Sentiment Analysis with Hierarchical Graph Convolutional Network.
Label Correction Model for Aspect-based Sentiment Analysis.
Attention Transfer Network for Aspect-level Sentiment Classification.
Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification.
Modeling language evolution and feature dynamics in a realistic geographic environment.
A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English.
IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP.
Linguistic Profiling of a Neural Language Model.
Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case.
Summarizing Medical Conversations via Identifying Important Utterances.
French Biomedical Text Simplification: When Small and Precise Helps.
Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Framework.
Extracting Adherence Information from Electronic Health Records.
BioMedBERT: A Pre-trained Biomedical Language Model for QA and IR.
TIMBERT: Toponym Identifier For The Medical Domain Based on BERT.
Enhancing Clinical BERT Embedding using a Biomedical Knowledge Base.
A Joint Learning Approach based on Self-Distillation for Keyphrase Extraction from Scientific Documents.
Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge.
Named Entity Recognition for Chinese biomedical patents.
Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions.
Author's Sentiment Prediction.
Arabizi Language Models for Sentiment Analysis.
Bayes-enhanced Lifelong Attention Networks for Sentiment Classification.
SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis.
RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion.
Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization.
Knowledge Graph Embeddings in Geometric Algebras.
Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution.
AprilE: Attention with Pseudo Residual Connection for Knowledge Graph Embedding.
Re-framing Incremental Deep Language Models for Dialogue Processing with Multi-task Learning.
Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey.
LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization.
Speaker-change Aware CRF for Dialogue Act Classification.
Improving Abstractive Dialogue Summarization with Graph Structures and Topic Words.
Generating Equation by Utilizing Operators : GEO model.
Multimodal Review Generation with Privacy and Fairness Awareness.
Leveraging HTML in Free Text Web Named Entity Recognition.
Predicting Stance Change Using Modular Architectures.
Neural Approaches for Natural Language Interfaces to Databases: A Survey.
PG-GSQL: Pointer-Generator Network with Guide Decoding for Cross-Domain Context-Dependent Text-to-SQL Generation.
Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of Swedish Learner Essays.
SQL Generation via Machine Reading Comprehension.
CEREC: A Corpus for Entity Resolution in Email Conversations.
Heterogeneous Graph Neural Networks to Predict What Happen Next.
Pointing to Subwords for Generating Function Names in Source Code.
Integrating External Event Knowledge for Script Learning.
A Representation Learning Approach to Animal Biodiversity Conservation.
Train Once, and Decode As You Like.
Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks.
Improving Sentiment Analysis over non-English Tweets using Multilingual Transformers and Automatic Translation for Data-Augmentation.
Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis.
Understanding Pre-trained BERT for Aspect-based Sentiment Analysis.
Affective and Contextual Embedding for Sarcasm Detection.
Regrexit or not Regrexit: Aspect-based Sentiment Analysis in Polarized Contexts.
A Unified Sequence Labeling Model for Emotion Cause Pair Extraction.
End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network.
From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation.
Making the Best Use of Review Summary for Sentiment Analysis.
METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis.
Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis.
A Symmetric Local Search Network for Emotion-Cause Pair Extraction.
Appraisal Theories for Emotion Classification in Text.
Is Killed More Significant than Fled? A Contextual Model for Salient Event Detection.
Hierarchical Chinese Legal event extraction via Pedal Attention Mechanism.
Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations.
MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing.
Catching Attention with Automatic Pull Quote Selection.
A Graph Representation of Semi-structured Data for Web Question Answering.
CharBERT: Character-aware Pre-trained Language Model.
Building Hierarchically Disentangled Language Models for Text Generation with Named Entities.
Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism.
Exploring Controllable Text Generation Techniques.
