EMNLP'21 | Dialogue System 对话系统

每天给你送来NLP技术干货！

---

编辑：机器学习算法与自然语言处理

在EMNLP2021包含Dialog的关键字的文章整理如下（也包括intent，slot，spoken language understanding，tracking这些词，欢迎补充）：

01

主会内容

• A Label-AwareBERTAttention Network for Zero-Shot Multi-Intent Detection in Spoken Language Understanding

• Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding

• Multilingual and Cross-Lingual Intent Detection from Spoken Data

• Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language Understanding

• Effectiveness of Pre-training for Few-shot Intent Classification

• Towards Making the Most of Dialogue Characteristics for Neural Chat Translation

• Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining

• Controllable Neural Dialogue Summarization with Personal Named Entity Planning

• GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation

• Graph Based Network with Contextualized Representations of Turns in Dialogue

• Automatically Exposing Problems with Neural Dialog Models

• MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks

• Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

• We’ve had this conversation before: A Novel Approach to Measuring Dialog Similarity

• CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation

• DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization

• Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems

• Contextual Rephrase Detection for Reducing Friction in Dialogue Systems

• Reference-Centric Models for Grounded Collaborative Dialogue

• Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding

• Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems

• Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration

• CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation

• AThree-StageLearningFramework for Low-ResourceKnowledge-GroundedDialogueGeneration

• Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue

• More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge

• Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks

• Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue Tasks

• Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation

• Don’t be Contradicted with Anything!CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

• Transferable Persona-Grounded Dialogues via Grounded Minimal Edits

• DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings

• Adaptive Bridge between Training and Inference for Dialogue Generation

• Smoothing Dialogue States for Open Conversational Machine Reading

• Exophoric Pronoun Resolution in Dialogues with Topic Regularization

• Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems

• Efficient Dialogue Complementary Policy Learning via DeepQ-network Policy and Episodic Memory Policy

• End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

• CSDS: A Fine-GrainedChinese Dataset for Customer Service Dialogue Summarization

• Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions

• Region under Discussion for visual dialog

• Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts

• Multi-Modal Open-Domain Dialogue

• Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection

• SIMMC2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations

• RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging

• MRF-Chat: Improving Dialogue withMarkov Random Fields

• Dialogue State Tracking with a Language Model using Schema-Driven Prompting

• MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents

• NDH-Full: Learning and Evaluating Navigational Agents on Full-Length Dialogue

• Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization

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

• Continual Learning in Task-Oriented Dialogue Systems

• Investigating Robustness of Dialog Models to Popular Figurative Language Constructs

• Effective Sequence-to-Sequence Dialogue State Tracking

• Learning Neural Templates for Recommender Dialogue System

• Proxy Indicators for the Quality of Open-domain Dialogues

• Q2:Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering

• Knowledge-Aware Graph-EnhancedGPT-2 for Dialogue State Tracking

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

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

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

• A Bag of Tricks for Dialogue Summarization

• Is Information Density Uniform in Task-Oriented Dialogues?

• Code-switched inspired losses for spoken dialog representations

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

• Athena 2.0: Contextualized Dialogue Management for anAlexaPrizeSocialBot

• Robust Retrieval Augmented Generation for Zero-shot Slot Filling

02

Findings论文

• An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling

• TWEETSUMM- A Dialog Summarization Dataset for Customer Service

• Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer

• A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems

• Learning to Ground Visual Objects for Visual Dialog

• KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals

• Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment

• Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions

• Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization

• Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation

• Improving End-to-End Task-Oriented Dialog System with A Simple Auxiliary Task

• A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization

• Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation

• TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

• Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser

• Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension

• Speaker Turn Modeling for Dialogue Act Classification

• SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks

• Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization

• DialogueTRM: Exploring Multi-Modal Emotional Dynamics in a Conversation

• Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation

• An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog

• Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration

• Probing Commonsense Explanation in Dialogue Response Generation

• FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning

• Task-Oriented Clustering for Dialogues

• An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next

• Speculative Sampling in Variational Autoencoders for Dialogue Response Generation

---

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

整理不易，还望给个在看！