KIT | KIT-Bibliothek | Impressum | Datenschutz

Error correction and extraction in request dialogs

Constantin, S. 1; Waibel, A. 1
1 Institut für Anthropomatik und Robotik (IAR), Karlsruher Institut für Technologie (KIT)

Abstract:

We propose a dialog system utility component that gets the two last utterances of a user and can detect whether the last utterance is an error correction of the second last utterance. If yes, it corrects the second last utterance according to the error correction in the last utterance. In addition, the proposed component outputs the extracted pairs of reparandum and repair entity. This component offers two advantages, learning the concept of corrections to avoid collecting corrections for every new domain and extracting reparandum and repair pairs, which offers the possibility to learn out of it. For the error correction one sequence labelling and two sequence to sequence approaches are presented. For the error correction detection these three error correction approaches can also be used and in addition, we present a sequence classification approach. One error correction detection and one error correction approach can be combined to a pipeline or the error correction approaches can be trained and used end-to-end to avoid two components. We modified the EPIC-KITCHENS-100 dataset to evaluate the approaches for correcting entity phrases in request dialogs. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000158055
Veröffentlicht am 21.04.2023
Scopus
Zitationen: 2
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2022
Sprache Englisch
Identifikator ISBN: 978-1-959429-36-4
KITopen-ID: 1000158055
Erschienen in Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022)
Veranstaltung 5th International Conference on Natural Language and Speech Processing (2022), Trient, Italien, 16.12.2022 – 17.12.2022
Verlag Association for Computational Linguistics (ACL)
Seiten 2-11
Externe Relationen Abstract/Volltext
Nachgewiesen in Scopus
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page