Wednesday Sept, 7
| 08:45 – 09:00 | Opening Remarks |
Robustness, Scalability, and Practicality of Conversational AI
| 10:00 – 10:30 | Break |
| 10:30 – 12:10 | Oral Session 1: “E2E dialogue systems” |
Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning, Atsumoto Ohashi and Ryuichiro Higashinaka [video]
Reducing Model Churn: Stable Re-training of Conversational Agents, Christopher Hidey, Fei Liu and Rahul Goel [video]
Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networks, Yen Ting Lin, Alexandros Papangelis, Seokhwan Kim and Dilek Hakkani-Tur [video]
Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design, A. Stevie Bergman, Gavin Abercrombie, Shannon Spruit, Dirk Hovy, Emily Dinan, Y-Lan Boureau and Verena Rieser [video]
| 12:10 – 13:00 | Lunch |
| 13:00 – 14:00 | Poster + Demo Session 1: |
Controllable User Dialogue Act Augmentation for Dialogue State Tracking, Chun-Mao Lai, Ming-Hao Hsu, Chao-Wei Huang and Yun-Nung Chen
Developing an argument annotation scheme based on a semantic classification of arguments, Lea Kawaletz, Heidrun Dorgeloh, Stefan Conrad and Zeljko Bekcic
Multi-Task Learning for Depression Detection in Dialogs, Chuyuan Li, Chloé Braud and Maxime Amblard
To laugh or not to laugh? The use of laughter to mark discourse structure, Bogdan Ludusan and Barbara Schuppler
QualityAdapt: an Automatic Dialogue Quality Estimation Framework, John Mendonca, Alon Lavie and Isabel Trancoso
Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues, Thibault Cordier, Tanguy Urvoy, Fabrice Lefèvre and Lina M. Rojas Barahona
DEMO: The DialPort tools, Jessica Huynh, Shikib Mehri, Cathy L. Jiao and Maxine Eskenazi
DEMO: GRILLBot: A multi-modal conversational agent for complex real-world tasks, Carlos Gemmell, Federico Rossetto, Iain Mackie, Paul Owoicho, Sophie Fischer and Jeff Dalton
| 14:00 – 15:00 | Oral Session 2: NLiHRI Special Session |
Dialog Acts for Task Driven Embodied Agents, Spandana Gella, Aishwarya Padmakumar, Patrick Lange and Dilek Hakkani-Tur [video]
Symbol and Communicative Grounding through Object Permanence with a Mobile Robot, Josue Torres-Foncesca, Catherine Henry and Casey Kennington [video]
Towards Personality-Aware Chatbots, Daniel Fernau, Stefan Hillmann, Nils Feldhus, Tim Polzehl and Sebastian Möller [video]
| 15:00 – 15:25 | NLiHRI Special Session Panel |
| 15:25 – 15:45 | Break |
| 15:45 – 16:00 | Sponsor Session: |
LivePerson
Alana
Apple
Toshiba
Furhat Robotics
| 16:00 – 17:00 | Remote Session 1: |
Towards Socially Intelligent Agents with Mental State Transition and Human Value, Liang Qiu, Yizhou Zhao, Yuan Liang, Pan Lu, Weiyan Shi, Zhou Yu and Song-Chun Zhu [video]
Automatic Verbal Depiction of a Brick Assembly for a Robot Instructing Humans, Rami Younes, Gérard Bailly, Frederic Elisei and Damien Pellier [video]
Are Interaction Patterns Helpful for Task-Agnostic Dementia Detection? An Empirical Exploration, Shahla Farzana and Natalie Parde [video]
EDU-AP: Elementary Discourse Unit based Argument Parser, Sougata Saha, Souvik Das and Rohini Srihari [video]
Using Transition Duration to Improve Turn-taking in Conversational Agents, Charles Threlkeld, Muhammad Umair and JP de Ruiter [video]
DG2: Data Augmentation Through Document Grounded Dialogue Generation, Qingyang Wu, Song Feng, Derek Chen, Sachindra Joshi, Luis Lastras and Zhou Yu [video]
| 17:00 – 18:00 | Remote Session 2: |
(NLiHRI) When can I Speak? Predicting initiation points for spoken dialogue agents, Siyan Li, Ashwin Paranjape and Christopher D. Manning [video]
Using Interaction Style Dimensions to Characterize Spoken Dialog Corpora, Nigel Ward [video]
Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention, Longfei Yang, Jiyi Li, Sheng Li and Takahiro Shinozaki [video]
Building a Knowledge-Based Dialogue System with Text Infilling, Qiang Xue, Tetsuya Takiguchi and Yasuo Ariki [video]
D&D: When to Say What and How: Adapting the Elaborateness and Indirectness of Spoken Dialogue Systems, Juliana Miehle, Wolfgang Minker, Stefan Ultes [video]
D&D: Cognitive and social delays in the initiation of conversational repair, Julia Beret Mertens and J. P. de Ruiter
D&D: Referential Communication Between Friends and Strangers in the Wild, Kris Liu, Trevor D’Arcey, Marilyn Walker, Jean Fox Tree [video]
| 18:00 | Drinks Reception |
Thursday Sept, 8
| _ | _ |
| 09:00 – 10:00 | Keynote 2: Angeliki Lazaridou [video] |
On opportunities and challenges on communicating using Large Language Models
| 10:00 – 10:30 | Break |
| 10:30 – 12:10 | Oral Session 3: “Generation” |
Generating Meaningful Topic Descriptions with Sentence Embeddings and LDA, Javier Miguel Sastre Martinez, Sean Gorman, Aisling Nugent and Anandita Pal [video]
How Well Do You Know Your Audience? Toward Socially-aware Question Generation, Ian Stewart and Rada Mihalcea [video]
GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers, Hsien-chin Lin, Christian Geishauser, Shutong Feng, Nurul Lubis, Carel van Niekerk, Michael Heck and Milica Gasic [video]
AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog, Tomáš Nekvinda and Ondřej Dušek [video]
| 12:10 – 13:00 | Lunch |
| 13:00 – 14:40 | Oral Session 4: “Deep dives into dialogue systems” |
A Systematic Evaluation of Response Selection for Open Domain Dialogue, Behnam Hedayatnia, Di Jin, Yang Liu and Dilek Hakkani-Tur [video]
Inferring Ranked Dialog Flows from Human-to-Human Conversations, Javier Miguel Sastre Martinez and Aisling Nugent [video]
Structured Dialogue Discourse Parsing, Ta-Chung Chi and Alexander Rudnicky [video]
“Do you follow me?”: A Survey of Recent Approaches in Dialogue State Tracking, Léo Jacqmin, Lina M. Rojas Barahona and Benoit Favre [video]
| 14:40 – 15:00 | Break |
| 15:00 – 16:00 | Remote Session 3: |
MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation, Fanghua Ye, Jarana Manotumruksa and Emine Yilmaz [video]
The Duration of a Turn Cannot be Used to Predict When It Ends, Charles Threlkeld and JP de Ruiter [video]
Getting Better Dialogue Context for Knowledge Identification by Leveraging Document-level Topic Shift, Nhat Tran and Diane Litman [video]
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent, Ethan A. Chi, Ashwin Paranjape, Abigail See, Caleb Chiam, Trenton Chang, Kathleen Kenealy, Swee Kiat Lim, Amelia Hardy, Chetanya Rastogi, Haojun Li, Alexander Iyabor, Yutong He, Hari Sowrirajan, Peng Qi, Kaushik Ram Sadagopan, Nguyet Minh Phu, Dilara Soylu, Jillian Tang, Avanika Narayan, Giovanni Campagna and Christopher D. Manning [video]
DeepCon: An End-to-End Multilingual Toolkit for Automatic Minuting of Multi-Party Dialogues, Aakash Bhatnagar, Nidhir Bhavsar and Muskaan Singh [video]
ICM : Intent and Conversational Mining from Conversation Logs, Sayantan Mitra, Roshni Ramnani, Sumit Ranjan and Shubhashis Sengupta [video]
| 16:00 – 17:00 | Remote Session 4: |
Entity-based De-noising Modeling for Controllable Dialogue Summarization, Zhengyuan Liu and Nancy Chen [video]
iEval: Interactive Evaluation Framework for Open-Domain Empathetic Chatbots, Ekaterina Svikhnushina, Anastasiia Filippova and Pearl Pu [video]
Unsupervised Domain Adaptation on Question-Answering System with Conversation Data, Amalia Istiqlali Adiba, Takeshi Homma and Yasuhiro Sogawa [video]
UniDU: Towards A Unified Generative Dialogue Understanding Framework, Zhi Chen, Lu Chen, Bei Chen, Libo Qin, Yuncong Liu, Su Zhu, Jian-Guang LOU and Kai Yu [video]
Advancing Semi-Supervised Task Oriented Dialog Systems by JSA Learning of Discrete Latent Variable Models, Yucheng Cai, Hong Liu, Zhijian Ou, Yi Huang and Junlan Feng [video]
| 17:00 – 18:00 | Remote Session 5: |
Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Dataset, Stefan Larson and Kevin Leach [video]
Dialogue Evaluation with Offline Reinforcement Learning, Nurul Lubis, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Michael Heck, Shutong Feng and Milica Gasic [video]
Disruptive Talk Detection in Multi-Party Dialogue within Collaborative Learning Environments with a Regularized User-Aware Network, Kyungjin Park, Hyunwoo Sohn, Wookhee Min, Bradford Mott, Krista Glazewski, Cindy E. Hmelo-Silver and James Lester [video]
Generating Discourse Connectives with Pre-trained Language Models: Conditioning on Discourse Relations Helps Reconstruct the PDTB, Symon Stevens-Guille, Aleksandre Maskharashvili, Xintong Li and Michael White [video]
Toward Self-Learning End-to-End Task-oriented Dialog Systems, Xiaoying ZHANG, Baolin Peng, Jianfeng Gao and Helen Meng [video]
| 19:30 | Banquet |
Friday Sept, 9
| _ | _ |
Unlimited discourse structures in the era of distant supervision, pre-trained language models and autoencoders
| 10:00 – 10:15 | Break |
| 10:15 – 11:30 | Oral Session 5: “Dynamics and Methods I” |
Combining Structured and Unstructured Knowledge in an Interactive Search Dialogue System, Svetlana Stoyanchev, Suraj Pandey, Simon Keizer, Norbert Braunschweiler and Rama Sanand Doddipatla [video]
How Much Does Prosody Help Turn-taking? Investigations using Voice Activity Projection Models, Erik Ekstedt and Gabriel Skantze [video]
What makes you change your mind? An empirical investigation in online group decision-making conversations, Georgi Karadzhov, Tom Stafford and Andreas Vlachos [video]
| 11:30 – 11:40 | Break |
| 11:40 – 12:55 | Oral Session 6: “Dynamics and Methods II” |
Dialogue Term Extraction using Transfer Learning and Topological Data Analysis, Renato Vukovic, Michael Heck, Benjamin Matthias Ruppik, Carel van Niekerk, Marcus Zibrowius and Milica Gasic [video]
Evaluating N-best Calibration of Natural Language Understanding for Dialogue Systems, Ranim Khojah, Alexander Berman and Staffan Larsson [video]
LAD: Language Models as Data for Zero-Shot Dialog, Shikib Mehri, Yasemin Altun and Maxine Eskenazi [video]
| 12:55 – 13:45 | Lunch |
| 13:45 – 14:45 | Poster + Demo Session 2: |
Improving Bot Response Contradiction Detection via Utterance Rewriting, Di Jin, Sijia Liu, Yang Liu and Dilek Hakkani-Tur
Comparison of Lexical Alignment with a Teachable Robot in Human-Robot and Human- Human-Robot Interactions, Yuya Asano, Diane Litman, Mingzhi Yu, Nikki Lobczowski, Timothy Nokes-Malach, Adriana Kovashka and Erin Walker
TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues, Po-Wei Lin, Shang-Yu Su and Yun-Nung Chen
User Satisfaction Modeling with Domain Adaptation in Task-oriented Dialogue System, Yan Pan, Mingyang Ma, Bernhard Pflugfelder and Georg Groh
N-best Response-based Analysis of Contradiction-awareness in Neural Response Generation Models, Shiki Sato, Reina Akama, Hiroki Ouchi, Ryoko Tokuhisa, Jun Suzuki and Kentaro Inui
DEMO: A Visually-Aware Conversational Robot Receptionist, Nancie A. Gunson, Daniel Hernandez Garcia, Weronika Sieińska, Angus Addlesee, Christian Dondrup, Oliver Lemon, Jose L. Part and Yanchao Yu
DEMO: Demonstrating EMMA: Embodied MultiModal Agent for Language-guided Action Execution in 3D Simulated Environments, Alessandro Suglia, Bhathiya Hemanthage, Malvina Nikandrou, George Pantazopoulos, Amit Parekh, Arash Eshghi, Claudio Greco, Ioannis Konstas, Oliver Lemon and Verena Rieser
DEMO: Simultaneous Job Interview System Using Multiple Semi-autonomous Agents, Haruki Kawai, Yusuke Muraki, Kenta Yamamoto, Divesh Lala, Koji Inoue and Tatsuya Kawahara
DEMO: A System For Robot Concept Learning Through Situated Dialogue, Benjamin Kane, Felix Gervits, Matthias Scheutz and Matthew Marge
| 14:45 – 15:15 | SIGDIAL Business Meeting |
| 15:15 | Closing and Best Paper Awards |
NOTE:
Oral sessions: 20 mins presentation + 5 mins Q&A
Remote long: 7 min video + 3 mins Q&A
Remote D&D: 7 mins + 3 mins Q&A
Remote short/demo: 4 mins video + 3 mins Q&A
Posters should be A0 size, portrait