Conversational system for information navigation based on POMDP with user focus tracking

Yoshino, Katsumi; Kawahara, Tatsuya

doi:10.1016/j.csl.2015.01.003

Cited by 25 publications

(25 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been many works on automatic backchannel generation, with most using prosodic features for either rule-based models (Ward and Tsukahara, 2000; Truong et al, 2010) or machine learning methods (Morency et al, 2008; Ozkan et al, 2010;Kawahara et al, 2015).…”

Section: Continuous Backchannel Generationmentioning

confidence: 99%

“…These systems are multimodal in nature, using human-like non-verbal behaviors to give feedback to the user. However, the backchannels are usually generated after the end of utterance and they do not necessarily create synchrony in the conversation (Kawahara et al, 2015). Moreover, the dialogue systems are still based on handcrafted keyword matching.…”

Section: Introductionmentioning

confidence: 99%

“…The second is to correctly pair this with an appropriate whquestion word to form a meaningful question. The basic wh-question words are similar for both English and Japanese.To detect the focus word we use a conditional random field classifier in previous work which uses part-of-speech tags and a phrase-level dependency tree (Yoshino and Kawahara, 2015). The model was trained with utterances from users interacting with two different dialogue systems.…”

mentioning

confidence: 99%

“…Our information navigation system basically provides information, but only one case in which the system uses the information-seeking function is confirmation (CO) to clarify the previous user intent. Dimension-specific functions support the general-purpose function; thus, minimum social obligation and turn-management functions are implemented as Greeting (GR) and Keep silent (KS).Dialogue modules for these functions are defined for the task of news navigation (Yoshino and Kawahara, 2015), and the call of these modules at each turn is managed by the POMDP-based manager. The call of system action is managed by the policy of POMDP, which takes into account the interests of the user (=user focus).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

2017

View full text Add to dashboard Cite

We are excited to welcome you to this year's SIGdial Conference, the 18th Annual Meeting of the Special Interest Group on Discourse and Dialogue. We are pleased to hold the conference in Saarbrücken on August 15-17th, co-located with SemDial 2017, and in close proximity to both INTERSPEECH 2017 and YRRSDS 2017, the Young Researchers' Roundtable on Spoken Dialog Systems.The SIGdial conference remains a premier publication venue for research in discourse and dialogue. This year, the program includes oral presentations, poster sessions, and one demo session. SIGdial 2017 also hosts three special sessions, two joint with SemDial 2017.We received 113 submissions this year. In only one previous year has there been a greater number of submissions to SIGdial. All long and short papers received at least 3 reviews. We carefully considered both the numeric ratings and the tenor of the comments in making our selections for the program. Overall, the members of the Program Committee did an excellent job in reviewing the submitted papers. We thank them for their important role in selecting the accepted papers and for helping to come up with a high quality program for the conference. We also thank Pierre Lison, Mentoring Chair for SIGdial 2017, for his dedicated work on the mentoring process. The goal of mentoring is to assist authors of papers that contain important ideas but lack clarity. In line with the SIGdial tradition, our aim has been to create a balanced program that accommodates as many favorably rated papers as possible. We accepted 29 long papers, 11 short papers and 7 demo presentations. These numbers give an overall acceptance rate of 41.6%. The rates separately for types of papers are 42% for long papers, 30% for short and 87% for demo submissions. Of the long papers, 18 were presented as oral presentations. The remaining 11 long papers and all the short papers were presented as posters, split into two poster sessions.This year SIGdial has three special sessions on topics of growing interest. The chosen sessions were (i) the Special Session on Negotiation Dialog organized by Amanda Stent, Aasish Pappu, Diane Litman and Marilyn Walker; (ii) the Second WOCHAT Special Session on Chatbots and Conversational Agents organized by Ryuichiro Higashinaka, Ron Artstein, Rafael E. Banchs, and Wolfgang Minker; and (iii) Special Session on Natural Language Generation for Dialog Systems organized by Marilyn Walker, Verena Rieser, Vera Demberg, Dietrich Klakow, Dilek Hakkani-Tur, David M. Howcroft and Shereen Oraby. These specialized topics brought diverse paper submissions to our technical program. At the conference, the special sessions also featured panel discussions and position talks, allowing for active engagement of the conference participants. This year, two of these special sessions, the one on negotiation and on conversational agents, are part of the joint SIGdial/SemDial program at the conference bringing both communities to participate in them. This year's SIGdial conference runs 3 full days compared to previous year...

show abstract

Section: Continuous Backchannel Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

2017

View full text Add to dashboard Cite

show abstract

“…In contrast, an information navigation system (Yoshino and Kawahara, 2015) to clarify ambiguous user goals through a dialogue was proposed. The system provides information about current talking topics with several dialogue acts of providing information according to the ky strength of the user's interest to the current topic.…”

Section: Introductionmentioning

confidence: 99%

Information Navigation System with Discovering User Interests

Yoshino¹,

Suzuki²,

Nakamura³

2017

Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

Self Cite

View full text Add to dashboard Cite

We demonstrate an information navigation system for sightseeing domains that has a dialogue interface for discovering user interests for tourist activities. The system discovers interests of a user with focus detection on user utterances, and proactively presents related information to the discovered user interest. A partially observable Markov decision process (POMDP)-based dialogue manager, which is extended with user focus states, controls the behavior of the system to provide information with several dialogue acts for providing information. We transferred the belief-update function and the policy of the manager from other system trained on a di↵erent domain to show the generality of defined dialogue acts for our information navigation system.

show abstract