German Question Answering in CRM Systems
| dc.contributor.author | Schäfter, Sophie | |
| dc.contributor.author | Zylowski, Thorsten | |
| dc.date.accessioned | 2021-12-14T10:56:54Z | |
| dc.date.available | 2021-12-14T10:56:54Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | We present a Question Answering (QA) approach within the context of Customer Relationship Management (CRM) systems in German which we applied to several use cases. However, we aim to generalize the suggested approach, so it can be applied to other domains. In this course, the subjects of tabular QA, extractive QA and Frequently Asked Questions (FAQ) are examined. Moreover, we reveal our findings regarding fine-tuning transformer models for QA and propose an automatic labelling mechanism that can be integrated into QA systems in order to simplify the creation of training data. We evaluated on various CRM-related data sources. The evaluation of the fine-tuned extractive QA pipeline resulted in an F1-score of 76.93 %. A qualitative analysis by domain experts showed that the tabular QA pipeline with translation and column name mapping leads to an accuracy of 40 %. | en |
| dc.identifier.doi | 10.18420/informatik2021-100 | |
| dc.identifier.isbn | 978-3-88579-708-1 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/37604 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik, Bonn | |
| dc.relation.ispartof | INFORMATIK 2021 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-314 | |
| dc.subject | Natural Language Processing | |
| dc.subject | Question Answering | |
| dc.subject | Information Retrieval | |
| dc.subject | Customer Relationship Management | |
| dc.title | German Question Answering in CRM Systems | en |
| gi.citation.endPage | 1220 | |
| gi.citation.startPage | 1213 | |
| gi.conference.date | 27. September - 1. Oktober 2021 | |
| gi.conference.location | Berlin | |
| gi.conference.sessiontitle | Workshop: Künstliche Intelligenz für kleine und mittlere Unternehmen (KI-KMU 2021) |
Dateien
Originalbündel
1 - 1 von 1