SIGDIAL Day 2 Thursday 8th September

Angeliki Lazaridou Staff Research Scientist /DeepMind


Time Session Room
09:00 – 10:00 KEYNOTE: 
Angeliki Lazaridou
10:00 – 10:30 BREAK
10:30 – 12:10 ORAL SESSION 3  –  “Generation”

  • o3.1 Generating Meaningful Topic Descriptions with Sentence Embeddings and LDA
  • o3.2 How Well Do You Know Your Audience? Toward Socially-aware Question Generation
  • o3.3 GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers
  • o3.4 AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog
12:10 – 13:00 LUNCH ROBOTARIUM
13:00 – 14:40 ORAL SESSION 4  –  “Deep dives into dialogue systems”

  • o4.1 A Systematic Evaluation of Response Selection for Open Domain Dialogue
  • o4.2 Inferring Ranked Dialog Flows from Human-to-Human Conversations
  • o4.3 Structured Dialogue Discourse Parsing
  • o4.4 “Do you follow me?”: A Survey of Recent Approaches in Dialogue State Tracking
14:40 – 15:00 BREAK PG Centre
15:00 – 16:00 REMOTE SESSION 3

  • r3.1 MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation
  • r3.2 The Duration of a Turn Cannot be Used to Predict When It Ends
  • r3.3 Getting Better Dialogue Context for Knowledge Identification by Leveraging Document-level Topic Shift
  • r3.4 Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
  • r3.5 DeepCon: An End-to-End Multilingual Toolkit for Automatic Minuting of Multi-Party Dialogues
  • r3.6 ICM : Intent and Conversational Mining from Conversation Logs
16:00 – 17:00 REMOTE SESSION 4

  • r4.1 Entity-based De-noising Modeling for Controllable Dialogue Summarization
  • r4.2 iEval: Interactive Evaluation Framework for Open-Domain Empathetic Chatbots
  • r4.3 Unsupervised Domain Adaptation on Question-Answering System with Conversation Data
  • r4.4 UniDU: Towards A Unified Generative Dialogue Understanding Framework
  • r4.5 Advancing Semi-Supervised Task Oriented Dialog Systems by JSA Learning of Discrete Latent Variable Models
17:00 – 18:00 REMOTE SESSION 5

  • r5.1 Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset
  • r5.2 Dialogue Evaluation with Offline Reinforcement Learning
  • r5.3 Disruptive Talk Detection in Multi-Party Dialogue within Collaborative Learning Environments with a Regularized User-Aware Network
  • r5.4 Generating Discourse Connectives with Pre-trained Language Models: Conditioning on Discourse Relations Helps Reconstruct the PDTB
  • r5.5 Toward Self-Learning End-to-End Task-oriented Dialog Systems
19:00 BANQUET Ghillie-Dhu