【AAAI2021】NLP所有方向论文列表（情感分析、句法、NER、对话/问答、关系抽取、KD等）...

点击上方，选择星标或置顶，每天给你送干货！

最近整理了下AAAI2021 NLP论文各个细方向的接收列表！应该还有几篇漏网之鱼，之后发现了补上~

AAAI2021接收论文PDF查看地址如下：

https://aaai.org/Conferences/AAAI-21/wp-content/uploads/2020/12/AAAI-21_Accepted-Paper-List.Main_.Technical.Track_.pdf

NLP细方向论文列表

情感分析

• Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis

• An Adaptive Hybrid Framework for Cross-Domain Aspect-Based Sentiment Analysis

• Bridging Towers of Multi-Task Learning with a Gating Mechanism for Aspect-Based Sentiment Analysis and Sequential Metaphor Identification

• Human-Level Interpretable Learning for Aspect-Based Sentiment Analysis

• A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis

• Quantum Cognitively Motivated Decision Fusion for Video Sentiment Analysis

• Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

• Segmentation of Tweets with URLs and its Applications to Sentiment Analysis

• A Neural Group-Wise Sentiment Analysis Model with Data Sparsity Awareness

句法分析

• Encoder-Decoder Based Unified Semantic Role Labeling with Label-Aware Syntax

• Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs

• Story Ending Generation with Multi-Level Graph Convolutional Networks over Dependency Trees

命名实体识别

• Multi-Modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance

• CrossNER: Evaluating Cross-Domain Named Entity Recognition

• A Supervised Multi-Head Self-Attention Network for Nested Named Entity Recognition

• Nested Named Entity Recognition with Partially-Observed TreeCRFs

• Continual Learning for Named Entity Recognition

• Knowledge-Aware Named Entity Recognition with Alleviating Heterogeneity

• Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model

• MTAAL: Multi-Task Adversarial Active Learning for Medical Named Entity Recognition and Normalization

人机对话/问答

• Reinforced History Backtracking for Conversational Question Answering

• Quantum-Inspired Neural Network for Conversational Emotion Recognition

• DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition

• Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

• NaturalConv: A Chinese Dialogue Dataset Towards Multi-Turn Topic-Driven Conversation

• Conversational Neuro-Symbolic Commonsense Reasoning

• Keyword-Guided Neural Conversational Model

• Infusing Multi-Source Knowledge with Heterogeneous Graph Neural Network for Emotional Conversation Generation

• MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations

• Knowledge-Driven Data Construction for Zero-Shot Evaluation in Commonsense Question Answering

• Reinforced History Backtracking for Conversational Question Answering

• What the Role Is vs. What Plays the Role: Semi-Supervised Event Argument Extraction via Dual Question Answering

• Regularizing Attention Networks for Anomaly Detection in Visual Question Answering50

• TSQA: Tabular Scenario Based Question Answering

• Unanswerable Question Correction in Question Answering over Personal Knowledge Base

• Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to Text Transformation

• Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-Shot Commonsense Question Answering

• Asking the Right Questions: Learning Interpretable Action Models through Query Answering

• HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions

关系抽取

• FL-MSRE: A Few-Shot Learning Based Approach to Multimodal Social Relation Extraction

• Multi-View Inference for Relation Extraction with Uncertain Knowledge

• GDPNet: Refining Latent Multi-View Graph for Relation Extraction

• Progressive Multi-Task Learning with Controlled information Flow for Joint Entity and Relation Extraction

• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction

• Document-Level Relation Extraction with Reconstruction

• Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

• Entity Structure Within and Throughout: Modeling Mention Dependencies for Document Level Relation Extraction

• Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training

• Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference

• A Unified Multi-Task Learning Framework for Joint Extraction of Entities and Relations

事件抽取

• GATE: Graph Attention Transformer Encoder for Cross-Lingual Relation and Event Extraction

• What the Role Is vs. What Plays the Role: Semi-Supervised Event Argument Extraction via Dual Question Answering

• Span-Based Event Coreference Resolution

机器翻译

• Self-Supervised Bilingual Syntactic Alignment for Neural Machine Translation

• Empirical Regularization for Synthetic Sentence Pairs in Unsupervised Neural Machine Translation8

• Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding

• Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance

• Finding Sparse Structure for Domain Specific Neural Machine Translation

• Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation

• Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information

• Synchronous Interactive Decoding for Multilingual Neural Machine Translation

• Accelerating Neural Machine Translation with Partial Word Embedding Compression

• DirectQE: Direct Pretraining for Machine Translation Quality Estimation

• We Don't Speak the Same Language: Interpreting Polarization through Machine Translation

知识图谱

• Dual Quaternion Knowledge Graph Embeddings

• Type-Augmented Relation Prediction in Knowledge Graphs

• ChronoR: Rotation Based Temporal Knowledge Graph Embedding

• PASSLEAF: A Pool-Based Semi-Supervised Learning Framework for Uncertain Knowledge Graph Embedding

• KG-BART: Knowledge Graph-Augmented Bart for Generative Commonsense Reasoning

• Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders

• GaussianPath: A Bayesian Multi-Hop Reasoning Framework for Knowledge Graph Reasoning

• Topology-Aware Correlations between Relations for Inductive Link Prediction in Knowledge Graphs

• Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy Generation Networks

• Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs

• Knowledge Graph Embeddings with Projective Transformations

• (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs

• Randomized Generation of Adversary-Aware Fake Knowledge Graphs to Combat Intellectual Property Theft

• Dynamic Knowledge Graph Alignment

• Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-Shot Commonsense Question Answering

阅读理解

• Semantics Altering Modifications for Evaluating Comprehension in Machine Reading

• Retrospective Reader for Machine Reading Comprehension

• Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension

• VisualMRC: Machine Reading Comprehension on Document Images

• A Bidirectional Multi-Paragraph Reading Model for Zero-Shot Entity Linking

• Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction

• Audio-Oriented Multimodal Machine Comprehension via Dynamic Inter- and Intra-Modality Attention

• Semantics Altering Modifications for Evaluating Comprehension in Machine Reading

文本生成

• A Theoretical Analysis of the Repetition Problem in Text Generation

• TextGAIL: Generative Adversarial Imitation Learning for Text Generation

• Towards Faithfulness in Open Domain Table-to-Text Generation from an Entity-Centric View

• Perception Score: A Learned Metric for Open-Ended Text Generation Evaluation

• Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text

• Write-a-Speaker: Text-Based Emotional and Rhythmic Talking-Head Generation

• Stylized Dialogue Response Generation Using Stylized Unpaired Texts

知识蒸馏

• PSSM-Distil: Protein Secondary Structure Prediction (PSSP) on Low-Quality PSSM by Knowledge Distillation with Contrastive Learning

• LRC-BERT: Latent-Representation Contrastive Knowledge Distillation for Natural Language Understanding

• Peer Collaborative Learning for Online Knowledge Distillation

• Few-Shot Class-Incremental Learning via Relation Knowledge Distillation

• Harmonized Dense Knowledge Distillation Training for Multi-Exit Architectures

• Diverse Knowledge Distillation for End-to-End Person Search

• Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation

• Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis

• ALP-KD: Attention-Based Layer Projection for Knowledge Distillation

• Progressive Network Grafting for Few-Shot Knowledge Distillation

• Show, Attend and Distill: Knowledge Distillation via Attention-Based Feature Matching

• Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks

• Reinforced Multi-Teacher Selection for Knowledge Distillation

少量或者零样本学习

• Tailoring Embedding Function to Heterogeneous Few-Shot Tasks by Global and Local Feature Adaptors

• Learning Intact Features by Erasing-Inpainting for Few-Shot Classification

• PTN: A Poisson Transfer Network for Semi-Supervised Few-Shot Learning

• Few-Shot Lifelong Learning

• Partial Is Better Than All: Revisiting Fine-Tuning Strategy for Few-Shot Learning

• Few-Shot Font Generation with Localized Style Representations and Factorization

• Few-Shot One-Class Classification via Meta-Learning

• Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph

• FL-MSRE: A Few-Shot Learning Based Approach to Multimodal Social Relation Extraction

• Learning a Few-Shot Embedding Model with Contrastive Learning

• Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

• Looking Wider for Better Adaptive Representation in Few-Shot Learning

• Few-Shot Class-Incremental Learning via Relation Knowledge Distillation

• Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition

• Task Cooperation for Semi-Supervised Few-Shot Learning

• SALNet: Semi-Supervised Few-Shot Text Classification with Attention-Based Lexicon Construction

• StarNet: Towards Weakly Supervised Few-Shot Object Detection

• Progressive Network Grafting for Few-Shot Knowledge Distillation

• Few-Shot Learning for Multi-Label Intent Detection

• Incremental Embedding Learning via Zero-Shot Translation

• Task Aligned Generative Meta-Learning for Zero-Shot Learning

• Knowledge-Driven Data Construction for Zero-Shot Evaluation in Commonsense Question Answering

• Generalized Zero-Shot Learning via Disentangled Representation

• DASZL: Dynamic Action Signatures for Zero-Shot Learning

• Semantic-Guided Reinforced Region Embedding for Generalized Zero-Shot Learning

• Extracting Zero-Shot Structured Information from Form-like Documents: Pretraining with Keys and Triggers

• A Bidirectional Multi-Paragraph Reading Model for Zero-Shot Entity Linking

• Leveraging Table Content for Zero-Shot Text-to-SQL with Meta-Learning

• Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting

• Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-Shot Commonsense Question Answering

跨领域

• Error-Aware Density Isomorphism Reconstruction for Unsupervised Cross-Domain Crowd Counting

• SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation17

• Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing

• An Adaptive Hybrid Framework for Cross-Domain Aspect-Based Sentiment Analysis

• CrossNER: Evaluating Cross-Domain Named Entity Recognition

• Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation

• Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation

• Embracing Domain Differences in Fake News: Cross-Domain Fake News Detection Using Multi-Modal Data

跨语言

• FILTER: An Enhanced Fusion Method for Cross-Lingual Language Understanding

• On the Importance of Word Order Information in Cross-Lingual Sequence Labeling

• XL-WSD: An Extra-Large and Cross-Lingual Evaluation Framework for Word Sense Disambiguation

• GATE: Graph Attention Transformer Encoder for Cross-Lingual Relation and Event Extraction

多语言

• How Linguistically Fair Are Multilingual Pre-Trained Language Models?

• Synchronous Interactive Decoding for Multilingual Neural Machine Translation

• Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition

• Analogy Training Multilingual Encoders

• Multilingual Transfer Learning for QA Using Translation as Data Augmentation

新bert改进模型

• RpBERT: A Text-Image Relation Propagation-Based BERT Model for Multimodal NER

• LRC-BERT: Latent-Representation Contrastive Knowledge Distillation for Natural Language Understanding

• U-BERT: Pre-Training User Representations for Improved Recommendation

• ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

• RareBERT: Transformer Architecture for Rare Disease Patient Identification Using Administrative Claims

• DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances

• Degree Planning with PLAN-BERT: Multi-Semester Recommendation Using Future Courses of Interest

多模态

• Audio-Oriented Multimodal Machine Comprehension via Dynamic Inter- and Intra-Modality Attention

• SMIL: Multimodal Learning with Severely Missing Modality

• RpBERT: A Text-Image Relation Propagation-Based BERT Model for Multimodal NER

• Confidence-Aware Non-Repetitive Multimodal Transformers for TextCaps

• Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding

• Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis

• FL-MSRE: A Few-Shot Learning Based Approach to Multimodal Social Relation Extraction

• Multi-Modal Multi-Label Emotion Recognition with Heterogeneous Hierarchical Message Passing

• Multi-Modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance

• Robust Multi-Modality Person Re-Identification

• Deep Probabilistic Imaging: Uncertainty Quantification and Multi-Modal Solution Characterization for Computational Imaging

• VMLoc: Variational Fusion for Learning-Based Multimodal Camera Localization

• MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records

• Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition

• Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers

• Learning Intuitive Physics with Multimodal Generative Models

• MERL: Multimodal Event Representation Learning in Heterogeneous Embedding Spaces

• Theoretical Analyses of Multi-Objective Evolutionary Algorithms on Multi-Modal Objectives

• Embracing Domain Differences in Fake News: Cross-Domain Fake News Detection Using Multi-Modal Data

• Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning

• Humor Knowledge Enriched Transformer for Understanding Multimodal Humor

• MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification

说个正事哈

由于微信平台算法改版，公号内容将不再以时间排序展示，如果大家想第一时间看到我们的推送，强烈建议星标我们和给我们多点点【在看】。星标具体步骤为：

（1）点击页面最上方“深度学习自然语言处理”，进入公众号主页。

（2）点击右上角的小点点，在弹出页面点击“设为星标”，就可以啦。

感谢支持，比心。

投稿或交流学习，备注：昵称-学校（公司）-方向，进入DL&NLP交流群。

方向有很多：机器学习、深度学习，python，情感分析、意见挖掘、句法分析、机器翻译、人机对话、知识图谱、语音识别等。

记得备注呦

推荐两个专辑给大家：

专辑 | 李宏毅人类语言处理2020笔记

专辑 | NLP论文解读

专辑 | 情感分析

整理不易，还望给个在看！