SIGdial 2019

20th Annual SIGdial Meeting on Discourse and Dialogue

SIGdial 2019

The 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2019) was held on September 11-13, 2019 at the KTH Royal Institute of Technology in Stockholm, Sweden.

The SIGdial venue provides a regular forum for the presentation of cutting edge research in discourse and dialogue to both academic and industry researchers. Continuing with a series of successful seventeen previous meetings, this conference spans the research interest area of discourse and dialogue. The conference is sponsored by the SIGDIAL organization, which serves as the Special Interest Group in discourse and dialogue for both ACL and ISCA.

Website: http://workshops.sigdial.org/conference20/

Keynotes

0:59:21

Learning Natural Language Interfaces with Neural Models

Mirella Lapata

1:01:24

Situated Interaction

Dan Bohus

1:02:08

The Many Facets of Dialog

Helen Meng

Oral Session 1: Policy and Knowledge

0:24:47

Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes

Chinnadhurai Sankar and Sujith Ravi

0:24:29

Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning

Stefan Ultes

0:27:10

Interactive Factual Knowledge Learning in Dialogues

Sahisnu Mazumder, Bing Liu, Shuai Wang and Nianzu Ma

Oral Session 2: Implications of Deep Learning for Dialogue Modeling

0:28:04

DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks

Semih Yavuz, Abhinav Rastogi, Guan-Lin Chao and Dilek Hakkani-Tur

0:13:17

Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability

Zhuoxuan Jiang, Xian-Ling Mao, Ziming Huang, Jie Ma and Shaochun Li

0:31:37

Unsupervised Dialogue Spectrum Generation for Log Dialogue Ranking

Xinnuo Xu, Yizhe Zhang, Lars Liden and Sungjin Lee

Oral Session 3: Generation and End-to-end Dialogue Systems

0:25:28

Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation

Bo-Hsiang Tseng, Paweł Budzianowski, Yen-chen Wu and Milica Gasic

0:24:53

Structured Fusion Networks for Dialog

Shikib Mehri, Tejas Srinivasan and Maxine Eskenazi

0:25:17

Flexibly-Structured Model for Task-Oriented Dialogues

Lei Shu, Piero Molino, Mahdi Namazifar, Hu Xu, Bing Liu, Huaixiu Zheng and Gokhan Tur

Oral Session 4: Understanding and Dialogue State Tracking

0:26:48

Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational AI: HERMIT NLU

Andrea Vanzo, Emanuele Bastianelli and Oliver Lemon

0:26:30

Dialog State Tracking: A Neural Reading Comprehension Approach

Shuyang Gao, Abhishek Sethi, Sanchit Agarwal, Tagyoung Chung and Dilek Hakkani-Tur

Oral Session 5: Acoustics

0:26:28

Cross-Corpus Data Augmentation for Acoustic Addressee Detection

Oleg Akhtiamov, Ingo Siegert, Alexey Karpov and Wolfgang Minker

0:25:56

A Scalable Method for Quantifying the Role of Pitch in Conversational Turn-Taking

Kornel Laskowski, Marcin Wlodarczak and Mattias Heldner

Oral Session 6: Evaluation and Data

0:26:08

A Large-Scale User Study of an Alexa Prize Chatbot: Effect of TTS Dynamism on Perceived Quality of Social Dialog

Michelle Cohn, Chun-Yen Chen and Zhou Yu

0:26:26

Influence of Time and Risk on Response Acceptability in a Simple Spoken Dialogue System

Andisheh Partovi and Ingrid Zukerman

0:27:05

Characterizing the Response Space of Questions: a Corpus Study for English and Polish

Jonathan Ginzburg, Zulipiye Yusupujiang, Chuyuan Li, Kexin Ren and Paweł Łupkowski

Oral Session 7: Discourse

0:24:37

SpaceRefNet: a neural approach to spatial reference resolution in a real city environment

Dmytro Kalpakchi and Johan Boye

0:18:22

Which aspects of discourse relations are hard to learn? Primitive decomposition for discourse relation classification

Charlotte Roze, Chloé Braud and Philippe Muller

0:23:31

Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks

Siddharth Varia, Christopher Hidey and Tuhin Chakrabarty

Panel

1:03:52

The Future of Dialogue Research

Phil Cohen - Moderator, Vikram Ramanarayanan, Sujith Ravi, Gabriel Skantze