Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen: https://doi.org/10.21256/zhaw-20320
Publikationstyp: Konferenz: Paper
Art der Begutachtung: Peer review (Publikation)
Titel: DoQA : accessing domain-specific FAQs via conversational QA
Autor/-in: Campos, Jon Ander
Otegi, Arantxa
Soroa, Aitor
Deriu, Jan Milan
Cieliebak, Mark
Agirre, Eneko
et. al: No
DOI: 10.18653/v1/2020.acl-main.652
10.21256/zhaw-20320
Tagungsband: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Seiten: 7302
Seiten bis: 7314
Angaben zur Konferenz: ACL 2020, Virtual, 5-10 July 2020
Erscheinungsdatum: 2020
Verlag / Hrsg. Institution: Association for Computational Linguistics
Sprache: Englisch
Schlagwörter: Question answering; Deep learning; Natural language processing
Fachgebiet (DDC): 004: Informatik
400: Sprache und Linguistik
Zusammenfassung: The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dataset with 2,437 dialogues and 10,917 QA pairs. The dialogues are collected from three Stack Exchange sites using the Wizard of Oz method with crowdsourcing. Compared to previous work, DoQA comprises well-defined information needs, leading to more coherent and natural conversations with less factoid questions and is multi-domain. In addition, we introduce a more realistic information retrieval (IR) scenario where the system needs to find the answer in any of the FAQ documents. The results of an existing, strong, system show that, thanks to transfer learning from a Wikipedia QA dataset and fine tuning on a single FAQ domain, it is possible to build high quality conversational QA systems for FAQs without in-domain training data. The good results carry over into the more challenging IR scenario. In both cases, there is still ample room for improvement, as indicated by the higher human upperbound.
URI: https://digitalcollection.zhaw.ch/handle/11475/20320
Volltext Version: Publizierte Version
Lizenz (gemäss Verlagsvertrag): CC BY 4.0: Namensnennung 4.0 International
Departement: School of Engineering
Organisationseinheit: Institut für Angewandte Informationstechnologie (InIT)
Publiziert im Rahmen des ZHAW-Projekts: LIHLITH - Learning to Interact with Humans by Lifelong Interaction with Humans
Enthalten in den Sammlungen:Publikationen School of Engineering

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
2020_Campos-etal_DoQA_ACL.pdf590.12 kBAdobe PDFMiniaturbild
Öffnen/Anzeigen


Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.