对话系统：
Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
Incremental Learning from Scratch for Task-Oriented Dialogue Systems
Joint Effects of Context and User History for Predicting Online Conversation Re-entries
Proactive Human-Machine Conversation with Explicit Conversation Goal
Pretraining Methods for Dialog Context Representation Learning
A Large-Scale Corpus for Conversation Disentanglement
Self-Supervised Dialogue Learning
What should I ask? Using conversationally informative rewards for goal-oriented visual dialog.
Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog
Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset
Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
Reinforced Dynamic Reasoning for Conversational Question Generation
Collaborative Dialogue in Minecraft
Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
Fine-Grained Sentence Functions for Short-Text Conversation
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems
Improving Neural Conversational Models with Entropy-Based Data Filtering
问答系统：
Unsupervised Question Answering by Cloze Translation
Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
Generating Question-Answer Hierarchies
Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data
Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network
Improving the Robustness of Question Answering Systems to Question Paraphrasing
ELI5: Long Form Question Answering
RankQA: Neural Question Answering with Answer Re-Ranking
Latent Retrieval for Weakly Supervised Open Domain Question Answering
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
Careful Selection of Knowledge to solve Open Book Question Answering
Learning Representation Mapping for Relation Detection in Knowledge
Base Question Answering
Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for multi-Hop QA
TW.EETQA: A Social Media Focused Question Answering Dataset