Daheim, Nico ; Thulke, David ; Dugast, Christian ; Ney, Hermann (2022)
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Mode.
2022 Conference on Empirical Methods in Natural Language Processing. Abu Dhabi, UAE (07.12.2022-11.12.2022)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes’ theorem.One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document based on the dialog context and generated response.We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets.Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model.Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output.Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Daheim, Nico ; Thulke, David ; Dugast, Christian ; Ney, Hermann |
| Art des Eintrags: | Bibliographie |
| Titel: | Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Mode |
| Sprache: | Englisch |
| Publikationsjahr: | Dezember 2022 |
| Verlag: | ACL |
| Buchtitel: | Findings of the Association for Computational Linguistics: EMNLP 2022 |
| Veranstaltungstitel: | 2022 Conference on Empirical Methods in Natural Language Processing |
| Veranstaltungsort: | Abu Dhabi, UAE |
| Veranstaltungsdatum: | 07.12.2022-11.12.2022 |
| URL / URN: | https://aclanthology.org/2022.findings-emnlp.98/ |
| Kurzbeschreibung (Abstract): | In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes’ theorem.One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document based on the dialog context and generated response.We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets.Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model.Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output.Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements. |
| Freie Schlagworte: | UKP_p_seditrah_factcheck, UKP_p_SERMAS |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 01 Mär 2023 08:17 |
| Letzte Änderung: | 09 Mär 2023 12:38 |
| PPN: | 505647834 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum