Shekhar, Ravi ; Baumgärtner, Tim ; Venkatesh, Aashish ; Bruni, Elia ; Bernadi, Raffaella ; Fernandez, Raquel (2018)
Ask No More: Deciding when to guess in referential visual dialogue.
27th International Conference on Computational Linguistics. Santa Fe, USA (20.-26.08.2018)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Our goal is to explore how the abilities brought in by a dialogue manager can be included in end-to-end visually grounded conversational agents. We make initial steps towards this general goal by augmenting a task-oriented visual dialogue model with a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess. Our analyses show that adding a decision making component produces dialogues that are less repetitive and that include fewer unnecessary questions, thus potentially leading to more efficient and less unnatural interactions.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2018 |
| Autor(en): | Shekhar, Ravi ; Baumgärtner, Tim ; Venkatesh, Aashish ; Bruni, Elia ; Bernadi, Raffaella ; Fernandez, Raquel |
| Art des Eintrags: | Bibliographie |
| Titel: | Ask No More: Deciding when to guess in referential visual dialogue |
| Sprache: | Englisch |
| Publikationsjahr: | 18 Januar 2018 |
| Verlag: | ACL |
| Buchtitel: | Proceedings of the 27th International Conference on Computational Linguistics |
| Veranstaltungstitel: | 27th International Conference on Computational Linguistics |
| Veranstaltungsort: | Santa Fe, USA |
| Veranstaltungsdatum: | 20.-26.08.2018 |
| URL / URN: | https://www.aclweb.org/anthology/C18-1104/ |
| Kurzbeschreibung (Abstract): | Our goal is to explore how the abilities brought in by a dialogue manager can be included in end-to-end visually grounded conversational agents. We make initial steps towards this general goal by augmenting a task-oriented visual dialogue model with a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess. Our analyses show that adding a decision making component produces dialogues that are less repetitive and that include fewer unnecessary questions, thus potentially leading to more efficient and less unnatural interactions. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 20 Jan 2021 15:46 |
| Letzte Änderung: | 20 Jan 2021 15:46 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum