Program Overview
Proceedings (@ACL Anthology)
Day-1 Sep. 18 | Day-2 Sep. 19 | Day-3 Sep. 20
DAY-1: Wednesday, September 18
- 09:30-10:00 Opening
- 10:00-11:40 Oral session 1: Discourse (Chair: Peter Bourgonje)
- Dialogue Discourse Parsing as Generation: a Sequence-to-Sequence LLM-based Approach
Chuyuan Li, Yuwei Yin and Giuseppe Carenini - Rhetorical Strategies in the UN Security Council: Rhetorical Structure Theory and Conflicts
Karolina Zaczynska and Manfred Stede - Elaborative Simplification for German-Language Texts
Freya Hewett, Hadi Asghari and Manfred Stede - Examining Gender and Power on Wikipedia Through Face and Politeness
Adil Soubki, Shyne E. Choi and Owen Rambow - ReALM: Reference Resolution As Language Modeling
Joel Ruben Antony Moniz, Soundarya Krishnan, Melis Ozyildirim, Prathamesh Saraf, Halim Cagri Ates, Yuan Zhang and Hong Yu
- Dialogue Discourse Parsing as Generation: a Sequence-to-Sequence LLM-based Approach
- 11:40-13:00 Lunch
- 13:00-14:40 Oral session 2: Special Session (GEMINI – Graph-based knowlEdge for Modelling Intelligent Natural Interaction) (Chair: Kristiina Jokinen)
- Dialog Flow Induction for Constrainable LLM-Based Chatbots
Stuti Agrawal, Pranav Pillai, Nishi Uppuluri, Revanth Gangi Reddy, Sha Li, Gokhan Tur, Dilek Hakkani-Tur and Heng Ji - Knowledge-Grounded Dialogue Act Transfer using Prompt-Based Learning for Controllable Open-Domain NLG
Alain Vazquez Risco, Angela Maria Ramirez, Neha Pullabhotla, Nan Qiang, Haoran Zhang, Marilyn Walker and Maria Ines Torres - Incremental Learning for Knowledge-Grounded Dialogue Systems in Industrial Scenarios
Izaskun Fernandez, Cristina Aceta, Cristina Fernandez, Maria Ines Torres, Aitor Etxalar, Ariane Mendez, Maia Agirre, Manuel Torralbo, Arantza Del Pozo, Joseba Agirre, Egoitz Artetxe and Iker Altuna - Anticipating Follow-Up Questions in Exploratory Information Search
Graham Wilcock - Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphs
Phillip Schneider, Nektarios Machner, Kristiina Jokinen and Florian Matthes
- Dialog Flow Induction for Constrainable LLM-Based Chatbots
- 14:40-15:00 Sponsors
- 15:00-15:30 Coffee break
- 15:30-17:00 Poster session 1
- (1) “Keep up the good work!”: Using Constraints in Zero Shot Prompting to Generate Supportive Teacher Responses
E. Margaret Perkoff, Angela Maria Ramirez, Sean von Bayern, Marilyn A. Walker and James Martin - (2) HelloThere: A Corpus of Annotated Dialogues and Knowledge Bases of Time-Offset Avatars
Alberto Chierici and Nizar Habash - (3) It Couldn’t Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning
Brielen Madureira and David Schlangen - (4) Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups
Zhiyang Qi and Michimasa Inaba - (5) StyEmp: Stylizing Empathetic Response Generation via Multi-Grained Prefix Encoder and Personality Reinforcement
Yahui Fu, Chenhui Chu and Tatsuya Kawahara - (6) Multi-Criteria Evaluation Framework of Selecting Response-worthy Chats in Live Streaming
Zhantao Lai and Kosuke Sato - (7) Generating Unexpected yet Relevant User Dialog Acts
Lucie Galland, Catherine Pelachaud and Florian Pecune - (8) Training LLMs to Recognize Hedges in Dialogues about Roadrunner Cartoons
Amie Paige, Adil Soubki, John Murzaku, Owen Rambow and Susan E. Brennan - (9) On the Controllability of Large Language Models for Dialogue Interaction
Nicolas Wagner and Stefan Ultes - (10) Divide and Conquer: Rethinking Ambiguous Candidate Identification in Multimodal Dialogues with Pseudo-Labelling
Bhathiya Supun Hemanthage, Christian Dondrup, Hakan Bilen and Oliver Lemon - (11) Self-Emotion Blended Dialogue Generation in Social Simulation Agents
Qiang Zhang, Jason Naradowsky and Yusuke Miyao - (12) Enhancing Model Transparency: A Dialogue System Approach to XAI with Domain Knowledge
Isabel Feustel, Niklas Rach, Wolfgang Minker and Stefan Ultes - (13) Affect Recognition in Conversations Using Large Language Models
Shutong Feng, Guangzhi Sun, Nurul Lubis, Wen Wu, Chao Zhang and Milica Gasic - (14) Sentiment-Aware Dialogue Flow Discovery for Interpreting Communication Trends
Patrícia Sofia Pereira Ferreira, Isabel Carvalho, Ana Alves, Catarina Silva and Hugo Gonçalo Oliveira - (15) Analyzing and Enhancing Clarification Strategies for Ambiguous References in Consumer Service Interactions
Changling Li, Yujian Gan, Zhenrong Yang, Youyang Chen, Xinxuan Qiu, Yanni Lin, Matthew Purver and Massimo Poesio - (16) Coherence-Based Dialogue Discourse Structure Extraction using Open-Source Large Language Models
Gaetano Cimino, Chuyuan Li, Giuseppe Carenini and Vincenzo Deufemia - (17) Transforming Slot Schema Induction with Generative Dialogue State Inference
James D. Finch, Boxin Zhao and Jinho D. Choi - (18) Scoring Coreference Chains with Split-Antecedent Anaphors
Silviu Paun, Juntao Yu, Nafise Sadat Moosavi, and Massimo Poesio
(paper from Dialogue & Discourse journal) - (19-Demo) Using Respiration for Enhancing Human-Robot Dialogue
Takao Obi and Kotaro Funakoshi - (20-Demo) Interactive Dialogue Interface for Personalized News Article Comprehension
Tomoya Higuchi and Michimasa Inaba
- (1) “Keep up the good work!”: Using Constraints in Zero Shot Prompting to Generate Supportive Teacher Responses
- 17:00-18:00 Keynote 1: Koji Inoue (Yeah, Well, Haha: Generating Non-linguistic Behaviors For Human-like Conversational Robots) (Chair: Vera Demberg)
- 18:00-20:00 Reception @Foyer
DAY-2: Thursday, September 19
- 09:00-10:20 Oral session 3: ML for Dialogue (Chair: Yun-Nung Chen)
- Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
Wonjun Lee, San Kim and Gary Geunbae Lee - Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
Benjamin Matthias Ruppik, Michael Heck, Carel van Niekerk, Renato Vukovic, Hsien-chin Lin, Shutong Feng, Marcus Zibrowius and Milica Gasic - Adaptive Open-Set Active Learning with Distance-Based Out-of-Distribution Detection for Robust Task-Oriented Dialog System
Sai Keerthana Goruganthu, Roland R. Oruche and Prasad Calyam - Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
Renato Vukovic, David Arps, Carel van Niekerk, Benjamin Matthias Ruppik, Hsien-chin Lin, Michael Heck and Milica Gasic
- Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
- 10:20-10:40 Coffee break
- 10:40-11:40 Keynote 2: Zhou Yu (AI Agents Beyond ChatGPT) (Chair: Stefan Ultes)
- 11:40-13:00 Lunch
- 13:00-14:20 Oral session 4: Education / Tutoring (Chair: Kallirroi Georgila)
- InteLLA: Intelligent Language Learning Assistant for Assessing Language Proficiency Through Interviews and Roleplays
Mao Saeki, Hiroaki Takatsu, Fuma Kurata, Shungo Suzuki, Masaki Eguchi, Ryuki Matsuura, Kotaro Takizawa, Sadahiro Yoshikawa and Yoichi Matsuyama - Curriculum-Driven Edubot: A Framework for Developing Language Learning Chatbots Through Synthesizing Conversational Data
Yu Li, Shang Qu, Jili Shen, Shangchao Min and Zhou Yu - Going beyond Imagination! Enhancing Multi-modal Dialogue Agents with Synthetic Visual Descriptions
Sameen Maruf, Ingrid Zukerman and Gholamreza Haffari - User Review Writing via Interview with Dialogue Systems
Yoshiki Tanaka and Michimasa Inaba
- InteLLA: Intelligent Language Learning Assistant for Assessing Language Proficiency Through Interviews and Roleplays
- 14:20-14:30 Introduction to Heian-Jingu Shrine
- 14:30-15:00 Coffee break
- 15:00-16:30 Poster session 2
- (1) Conversational Feedback in Scripted versus Spontaneous Dialogues: A Comparative Analysis
Ildiko Pilan, Laurent Prévot, Hendrik Buschmeier and Pierre Lison - (2) Exploring the Use of Natural Language Descriptions of Intents for Large Language Models in Zero-shot Intent Classification
Taesuk Hong, Youbin Ahn, Dongkyu Lee, Joongbo Shin, Seungpil Won, Janghoon Han, Stanley Jungkyu Choi and Jungyun Seo - (3) Voice and choice: Investigating the role of prosodic variation in request compliance and perceived politeness using conversational TTS
Eva Szekely, Jeff Higginbotham and Francesco Possemato - (4) A Dialogue Game for Eliciting Balanced Collaboration
Isidora Jeknic, David Schlangen and Alexander Koller - (5) Improving Speech Recognition with Jargon Injection
Minh-Tien Nguyen, Tuan-Hai Luu, Xuan-Quang Nguyen, Tung-Duong Nguyen and Jeff Yang - (6) Optimizing Code-Switching in Conversational Tutoring Systems: A Pedagogical Framework and Evaluation
Zhengyuan Liu, Stella Xin Yin and Nancy Chen - (7) ECoh: Turn-level Coherence Evaluation for Multilingual Dialogues
John Mendonca, Isabel Trancoso and Alon Lavie - (8) An Investigation Into Explainable Audio Hate Speech Detection
Jinmyeong An, Wonjun Lee, Yejin Jeon, Jungseul Ok, Yunsu Kim and Gary Geunbae Lee - (9) Mhm… Yeah? Okay! Evaluating the Naturalness and Communicative Function of Synthesized Feedback Responses in Spoken Dialogue
Carol Figueroa, Marcel de Korte, Magalie Ochs and Gabriel Skantze - (10) Generalizing across Languages and Domains for Discourse Relation Classification
Peter Bourgonje and Vera Demberg - (11) BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation
Suvodip Dey and Maunendra Sankar Desarkar - (12) Cross-lingual Transfer and Multilingual Learning for Detecting Harmful Behaviour in African Under-Resourced Language Dialogue
Tunde Oluwaseyi Ajayi, Mihael Arcan and Paul Buitelaar - (13) A Few-shot Approach to Task-oriented Dialogue Enhanced with Chitchat
Armand Stricker and Patrick Paroubek - (14) Exploration of Human Repair Initiation in Task-oriented Dialogue: A Linguistic Feature-based Approach
Anh Ngo, Dirk Heylen, Nicolas Rollet, Catherine Pelachaud and Chloé Clavel - (15) Comparing Pre-Trained Embeddings and Domain-Independent Features for Regression-Based Evaluation of Task-Oriented Dialogue Systems
Kallirroi Georgila - (16) Question Type Prediction in Natural Debate
Zlata Kikteva, Alexander Trautsch, Steffen Herbold and Annette Hautli-Janisz - (17) MemeIntent: Benchmarking Intent Description Generation for Memes
Jeongsik Park, Khoi PN Nguyen, Terrence Li, Suyesh Shrestha, Megan Kim Vu, Jerry Yining Wang and Vincent Ng - (18) Automating PTSD Diagnostics in Clinical Interviews: Leveraging Large Language Models for Trauma Assessments
Sichang Tu, Abigail Powers, Natalie Merrill, Negar Fani, Sierra Carter, Stephen Doogan and Jinho D. Choi - (19-Demo) DialBB: A Dialogue System Development Framework as an Educational Material
Mikio Nakano and Kazunori Komatani - (20-Demo) A Multimodal Dialogue System to Lead Consensus Building with Emotion-Displaying
Shinnosuke Nozue, Yuto Nakano, Shoji Moriya, Tomoki Ariyama, Kazuma Kokuta, Suchun Xie, Kai Sato, Shusaku Sone, Ryohei Kamei, Reina Akama, Yuichiroh Matsubayashi and Keisuke Sakaguchi
- (1) Conversational Feedback in Scripted versus Spontaneous Dialogues: A Comparative Analysis
- 16:30-18:00 Excursion to Heian-Jingu Shrine（平安神宮）
- 18:00-20:30 Banquet @Heian Jingu Kaikan（平安神宮会館）
DAY-3: Friday, September 20
- 09:00-10:20 Oral session 5: Persona / Emotions (Chair: Mikio Nakano)
- PersonaCLR: Evaluation Model for Persona Characteristics via Contrastive Learning of Linguistic Style Representation
Michimasa Inaba - DiagESC: Dialogue Synthesis for Integrating Depression Diagnosis into Emotional Support Conversation
Seungyeon Seo and Gary Geunbae Lee - Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation
Shutong Feng, Hsien-chin Lin, Christian Geishauser, Nurul Lubis, Carel van Niekerk, Michael Heck, Benjamin Matthias Ruppik, Renato Vukovic and Milica Gasic - Estimating the Emotional Valence of Interlocutors Using Heterogeneous Sensors in Human-Human Dialogue
Jingjing Jiang, Ao Guo and Ryuichiro Higashinaka
- PersonaCLR: Evaluation Model for Persona Characteristics via Contrastive Learning of Linguistic Style Representation
- 10:20-10:40 Coffee break
- 10:40-11:40 Panel Discussion: “Future of Dialogue Research”
- Moderator: Tatsuya Kawahara (Kyoto University)
- Panelists:
- Vera Demberg (Saarland University)
- Stefan Ultes (University of Bamberg)
- Koichiro Yoshino (Tokyo Institute of Technology)
- Ingrid Zukerman (Monash University)
- Vivian Chen (National Taiwan University)
- 11:40-13:00 Lunch
- 13:00-14:20 Oral session 6: Interaction (Chair: Koichiro Yoshino)
- The Gap in the Strategy of Recovering Task Failure between GPT-4V and Humans in a Visual Dialogue
Ryosuke Oshima, Seitaro Shinagawa and Shigeo Morishima - MindDial: Enhancing Conversational Agents with Theory-of-Mind for Common Ground Alignment and Negotiation
Shuwen Qiu, Mingdian Liu, Song-Chun Zhu and Zilong Zheng - An Open Intent Discovery Evaluation Framework
Grant Anderson, Emma Hart, Dimitra Gkatzia and Ian Beaver - Toximatics: Towards Understanding Toxicity in Real-Life Social Situations
Mayukh Das and Wolf-Tilo Balke
- The Gap in the Strategy of Recovering Task Failure between GPT-4V and Humans in a Visual Dialogue
- 14:20-14:50 Coffee break
- 14:50-15:50 Business meeting
- 15:50-16:20 Award & Closing
Notice to presenters
Oral presentation:
The presenter is required to arrive at the symposium hall 5 minutes before the session starts and introduce themselves to the session chairs. The projector system is compatible only with HDMI connections, so presenters should use their laptop PCs for the presentation and bring an HDMI connector.
For audio playback, the presenter must use the audio line (mini-jack), as the HDMI system in use does not support audio output. If the presenter’s laptop lacks a mini-jack port, they should also bring an adapter.
Poster / Demo presentation:
The presenters should set up their poster/demo 5-10 minutes in the designated place prior to the session. The poster can be placed any time of the day, but must be removed by the end of the day. The size of the poster panel is 210cm(H) x 90cm (W), which is good for an A0-size portrait format poster.
Wifi:
eduroam is available in the conference venue. Please get/update your eduroam account if possible.