Petrak, Dominic ; Tran, Thy Thy ; Gurevych, Iryna (2024)
Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues.
29th Conference on Empirical Methods in Natural Language Processing. Miami, USA (12.11.2024 - 16.11.2024)
doi: 10.18653/v1/2024.findings-emnlp.264
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialogue systems. However, the influence of such information on task completion and factual consistency, which are important criteria for task-oriented and document-grounded dialogues, is not yet known. To address this, we introduce FEDI, the first English task-oriented and document-grounded dialogue dataset annotated with this information. Our experiments with Flan-T5, GPT-2 and Llama 2 show a particularly positive impact on task completion and factual consistency. Participants in our human evaluation reported that the responses generated by the feedback-trained models were more informative (Flan-T5 and GPT-2), relevant and factual consistent (Llama 2).
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Petrak, Dominic ; Tran, Thy Thy ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues |
| Sprache: | Englisch |
| Publikationsjahr: | November 2024 |
| Verlag: | ACL |
| Buchtitel: | EMNLP 2024: The 2024 Conference on Empirical Methods in Natural Language Processing: Findings of EMNLP 2024 |
| Veranstaltungstitel: | 29th Conference on Empirical Methods in Natural Language Processing |
| Veranstaltungsort: | Miami, USA |
| Veranstaltungsdatum: | 12.11.2024 - 16.11.2024 |
| DOI: | 10.18653/v1/2024.findings-emnlp.264 |
| URL / URN: | https://aclanthology.org/2024.findings-emnlp.264/ |
| Kurzbeschreibung (Abstract): | Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialogue systems. However, the influence of such information on task completion and factual consistency, which are important criteria for task-oriented and document-grounded dialogues, is not yet known. To address this, we introduce FEDI, the first English task-oriented and document-grounded dialogue dataset annotated with this information. Our experiments with Flan-T5, GPT-2 and Llama 2 show a particularly positive impact on task completion and factual consistency. Participants in our human evaluation reported that the responses generated by the feedback-trained models were more informative (Flan-T5 and GPT-2), relevant and factual consistent (Llama 2). |
| Freie Schlagworte: | UKP_p_SERMAS |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 17 Dez 2024 11:37 |
| Letzte Änderung: | 17 Dez 2024 11:39 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum