Conversational role assignment problem in multi-party dialogues Natasa Jovanovic Dennis Reidsma Rutger Rienks TKI group University of Twente.

Slides:



Advertisements
Similar presentations
APPROACHES TO T&L Language
Advertisements

Machine Learning Approaches to the Analysis of Large Corpora : A Survey Xunlei Rose Hu and Eric Atwell University of Leeds.
A Human-Centered Computing Framework to Enable Personalized News Video Recommendation (Oh Jun-hyuk)
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
OpenDial Framework Svetlana Stoyanchev SDS seminar 3/23.
Modelling and Analyzing Multimodal Dyadic Interactions Using Social Networks Sergio Escalera, Petia Radeva, Jordi Vitrià, Xavier Barò and Bogdan Raducanu.
ENTERFACE’08 Multimodal Communication with Robots and Virtual Agents.
Collection and Analysis of Multimodal Interaction in Direction Giving Dialogues Seikei University Takeo TsukamotoYumi Muroya Masashi Okamoto Yukiko Nakano.
REACTION REACTION Workshop Task 1 – Progress Report & Plans Lisbon, PT and Austin, TX Mário J. Silva University of Lisbon, Portugal.
23-May-151 Multiparty Communication with a Tour Guide ECA Aleksandra Čereković HOTLab group Department of telecommunications Faculty of electrical engineering.
ETHNOGRAPHY OF COMMUNICATION As a domain of inquiry, linguistic anthropology starts from the theoretical assumption that words matter and from the empirical.
ETHNOGRAPHY OF COMMUNICATION As a domain of inquiry, linguistic anthropology starts from the theoretical assumption that words matter and from the empirical.
ETHNOGRAPHY OF COMMUNICATION
Unsupervised Clustering in Multimodal Multiparty Meeting Analysis.
Presented by Zeehasham Rasheed
Multimodality in Conversation Analysis: A case of Greek TV Interviews Maria Koutsombogera *, Lida Touribaba*, Harris Papageorgiou.
Communicating with Avatar Bodies Francesca Barrientos Computer Science UC Berkeley 8 July 1999 HCC Research Retreat.
System Management Network Environment Vehicle Characteristics Traveler Characteristics System Traveler Influencing Factors Traveler: traveler characteristics,
1 IUT de Montreuil Université Paris 8 Emotion in Interaction: Embodied Conversational Agents Catherine Pelachaud.
1 How To Annotate Interactions Using Dialog Function Units (Part 1) by Michal Novemsky (with the help of Becky Passonneau & Eddie Kang) CCLS, Columbia.
Building the Design Studio of the Future Aaron Adler Jacob Eisenstein Michael Oltmans Lisa Guttentag Randall Davis October 23, 2004.
Unit 1 Language and Learning Methodology Unit 1 Language and learning I.How do we learn language ? 1 ) How do we learn our own language ? 2 ) How do.
Discussions and Oral Presentations as Teaching Material in English for Medicine Zorica Antic Natasa Milosavljevic English language department Faculty of.
Towards an integrated scheme for semantic annotation of multimodal dialogue data Volha Petukhova and Harry Bunt.
Dialogue Act Tagging Using TBL Sachin Kamboj CISC 889: Statistical Approaches to NLP Spring 2003 September 14, 2015September 14, 2015September 14, 2015.
Qualitative Analysis Information Studies Division Research Workshop Elisabeth Logan.
Recognition of meeting actions using information obtained from different modalities Natasa Jovanovic TKI University of Twente.
Effective Public Speaking Chapter # 3 Setting the Scene for Community in a Diverse Culture.
Working group on multimodal meaning representation Dagstuhl workshop, Oct
Issues in Dialogue Management for Multiparty Dialogue David Traum University of Southern California Institute for Creative Technologies (ICT)
COMPUTER ASSISTED / AIDED LANGUAGE LEARNING (CALL) By: Sugeili Liliana Chan Santos.
Chapter 7. BEAT: the Behavior Expression Animation Toolkit
© Olena Chernenko/Vetta/Getty Images Lamb, Hair, McDaniel Chapter 18 Social Media and Marketing © Cengage Learning All Rights Reserved.
APML, a Markup Language for Believable Behavior Generation Soft computing Laboratory Yonsei University October 25, 2004.
Incorporating Extra-linguistic Information into Reference Resolution in Collaborative Task Dialogue Ryu Iida Shumpei Kobayashi Takenobu Tokunaga Tokyo.
SPEECH CONTENT Spanish Expressive Voices: Corpus for Emotion Research in Spanish R. Barra-Chicote 1, J. M. Montero 1, J. Macias-Guarasa 2, S. Lufti 1,
Exploiting Subjective Annotations Dennis Reidsma and Rieks op den Akker Human Media Interaction University of Twente
Towards multimodal meaning representation Harry Bunt & Laurent Romary LREC Workshop on standards for language resources Las Palmas, May 2002.
Reconceptualizing Mathematical Objects as Mediating Discursive Metaphors Aaron Weinberg Ithaca College.
SPEECH AND WRITING. Spoken language and speech communication In a normal speech communication a speaker tries to influence on a listener by making him:
Issues in Multiparty Dialogues Ronak Patel. Current Trend  Only two-party case (a person and a Dialog system  Multi party (more than two persons Ex.
Non-verbal Communication. How necessary is it to use and interpret it?
ENTERFACE 08 Project 1 “MultiParty Communication with a Tour Guide ECA” Mid-term presentation August 19th, 2008.
Conversation Analysis Introduction to Conversation Analysis 2e Anthony J. Liddicoat, March 2011.
VERBAL AND NONVERBAL COMMUNICATION BUILDING TRANSACTIONAL PROCESSES.
Communication Additional Notes. Communication Achievements 7% of all communication is accomplished Verbally. 55% of all communication is achieved through.
Speaking while monitoring addressees for understanding Torsten Jachmann Herbert H. Clark and Meredyth A. Krych Seminar „Gaze as function of.
Recognizing Stances in Online Debates Unsupervised opinion analysis method for debate-side classification. Mine the web to learn associations that are.
ADRESS FORMS AND POLITENESS Second person- used when the subject of the verb in a sentence is the same as the individual to.
Language and Gender. Language and Gender is… Language and gender is an area of study within sociolinguistics, applied linguistics, and related fields.
International Conference on Fuzzy Systems and Knowledge Discovery, p.p ,July 2011.
1/17/20161 Emotion in Meetings: Business and Personal Julia Hirschberg CS 4995/6998.
First Language Acquisition
ENTERFACE 08 Project #1 “ MultiParty Communication with a Tour Guide ECA” Final presentation August 29th, 2008.
Goteborg University Dialogue Systems Lab Comments on ”A Framework for Dialogue Act Specification” 4th Workshop on Multimodal Semantic Representation January.
R ITSUMEIKAN 13 th International Conference on Multimodal Interaction (ICMI 2011) Alicante, Spain, Nov. 16th, 2011 COMmunication Software Lab. Making Virtual.
SEESCOASEESCOA SEESCOA Meeting Activities of LUC 9 May 2003.
Understanding Naturally Conveyed Explanations of Device Behavior Michael Oltmans and Randall Davis MIT Artificial Intelligence Lab.
Verbal Communication. Oral Communication involves what?
ETHNOGRAPHY OF COMMUNICATION. An ethnography of communication includes descriptions of all explicit and implicit norms for communication, detailing aspects.
WP6 Emotion in Interaction Embodied Conversational Agents WP6 core task: describe an interactive ECA system with capabilities beyond those of present day.
Presented By Meet Shah. Goal  Automatically predicting the respondent’s reactions (accept or reject) to offers during face to face negotiation by analyzing.
Non Verbal Communication. Program Objectives (1 of 2)  Hone your interpersonal advantages while interacting with others.  Recognize how the eyes, face,
Grounding by nodding GESPIN 2009, Poznan, Poland
Approaches to Discourse Analysis
For Evaluating Dialog Error Conditions Based on Acoustic Information
Spoken Dialog System.
Studying Spoken Language Text 17, 18 and 19
Emer Gilmartin, Carl Vogel, ADAPT Centre Trinity College Dublin
CSD 232 • Descriptive Phonetics Eulenberg/Farhad Spring Semester 2011
Presentation transcript:

Conversational role assignment problem in multi-party dialogues Natasa Jovanovic Dennis Reidsma Rutger Rienks TKI group University of Twente

Outline Research tasks at TKI Research tasks at TKI  Interpretation of multimodal human- human communication in the meetings Conversational Role Assignment Problem (CRAP) Conversational Role Assignment Problem (CRAP)  Towards automatic addressee detection

A framework for multimodal interaction research

Multimodal annotation tool

Who is talking to whom? CRAP as one of the main issues in multi- parity conversation (Traum 2003.) CRAP as one of the main issues in multi- parity conversation (Traum 2003.) Taxonomy of conversational roles (Herbert K. Clark) Taxonomy of conversational roles (Herbert K. Clark) speakeraddressee side participant all participants bystander eavesdropper all listener

Our goal: Our goal:  Automatic addressee identification in small group discussions Addressees in meeting conversations: single participant, group of people, whole audience Addressees in meeting conversations: single participant, group of people, whole audience Importance of the issue of addressing in multi-party dialogues Importance of the issue of addressing in multi-party dialogues

Addressing mechanisms What are relevant sources of information for addressee identification in the face-to-face meeting conversations? What are relevant sources of information for addressee identification in the face-to-face meeting conversations? How does the speaker express who is the addressee of his utterance? How does the speaker express who is the addressee of his utterance? How can we combine all this information in order to determine the addressee of the utterance? How can we combine all this information in order to determine the addressee of the utterance?

Sources of information Speech Speech  Linguistic markers  word classes: personal pronouns, determiners in combination with personal pronouns, possessive pronouns and adjectives, indefinite pronouns, etc.  Name detection ( vocatives)  Dialogue acts Gaze direction Gaze direction Pointing gestures Pointing gestures Context categories(features) Context categories(features)

Dialogue Acts and Addressee detection (I) How many addresses may have an utterance? How many addresses may have an utterance? According to dialog act theory an utterance or an utterance segment may have more than one conversational function. According to dialog act theory an utterance or an utterance segment may have more than one conversational function. Each DA has a addressee ==> an utterance may have several addresses Each DA has a addressee ==> an utterance may have several addresses

Dialogue Acts and Addressee detection (II) MRDA (Meeting Recorder Dialogue Acts)– tag set for labeling multiparty face to face meetings (ICSI) MRDA (Meeting Recorder Dialogue Acts)– tag set for labeling multiparty face to face meetings (ICSI) We use a huge subset of the MRDA set which is organized on two levels: We use a huge subset of the MRDA set which is organized on two levels:  Forward looking functions (FLF )  Backward looking functions (BLF)

Non-verbal features Gaze Gaze  Contribution of the gaze to the addressee detection is dependent on: participants’ location (visible area), utterance length, current meeting action  Turn-taking behavior and addressing behavior Gesture ( pointing at a person) Gesture ( pointing at a person)  TALK_TO (X,Y) AND POINT_TO (X,Y)  TALK_TO( X,Y) AND POINT_TO (X,Z) – X talk to Y about Z

Context categories Bunt: “totality of conditions that may influence understanding and generation of communicative behavior” Bunt: “totality of conditions that may influence understanding and generation of communicative behavior”  Local context is an aspect of context that can be changed through communication Context categories: Context categories:  Interaction history ( verbal and non-verbal)  Meeting action history  Spatial context (participants’ location, distance, visible area, etc. )  User context (name, gender, roles, etc. )

Towards an automatic addressee detection Manual or automatic features annotation? Manual or automatic features annotation? An automatic target interpreter has to deal with uncertainty An automatic target interpreter has to deal with uncertainty Methods: Methods:  Rule-based method  Statistical method ( Bayesian networks)

Rule-based method 1. Processing information obtained from the utterance ( linguistic markers, vocatives, DA). The result is a list of possible addressees with corresponding probabilities 1. Eliminate cases where target is completely determined (for instance, name in vocative form) 2. Set of rules for BLF 3. Set of rules for FLF 2. Processing gaze and gesture information adding the additional probability values to the candidates

Meeting actions and addressee detection Automatic addressee detection method can be applied to the whole meeting Automatic addressee detection method can be applied to the whole meeting Knowledge about the current meeting action as well as about meeting actions history may help to better recognize the addressee of a dialogue act. Knowledge about the current meeting action as well as about meeting actions history may help to better recognize the addressee of a dialogue act.

Future works Development of multimodal annotation tool Development of multimodal annotation tool Data annotation for Data annotation for  training and evaluating statistical models  obtaining inputs for rule-based methods New meeting scenarios for research in addressing New meeting scenarios for research in addressing