Discovering Dialogue Slots with Weak Supervision

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440539" target="_blank" >RIV/00216208:11320/21:10440539 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2021.acl-long.189" target="_blank" >https://aclanthology.org/2021.acl-long.189</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2021.acl-long.189" target="_blank" >10.18653/v1/2021.acl-long.189</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Discovering Dialogue Slots with Weak Supervision

Popis výsledku v původním jazyce

Task-oriented dialogue systems typically require manual annotation of dialogue slots in training data, which is costly to obtain. We propose a method that eliminates this requirement: We use weak supervision from existing linguistic annotation models to identify potential slot candidates, then automatically identify domain-relevant slots by using clustering algorithms. Furthermore, we use the resulting slot annotation to train a neural-network-based tagger that is able to perform slot tagging with no human intervention. This tagger is trained solely on the outputs of our method and thus does not rely on any labeled data. Our model demonstrates state-of-the-art performance in slot tagging without labeled training data on four different dialogue domains. Moreover, we find that slot annotations discovered by our model significantly improve the performance of an end-to-end dialogue response generation model, compared to using no slot annotation at all.

Název v anglickém jazyce

Discovering Dialogue Slots with Weak Supervision

Popis výsledku anglicky

Task-oriented dialogue systems typically require manual annotation of dialogue slots in training data, which is costly to obtain. We propose a method that eliminates this requirement: We use weak supervision from existing linguistic annotation models to identify potential slot candidates, then automatically identify domain-relevant slots by using clustering algorithms. Furthermore, we use the resulting slot annotation to train a neural-network-based tagger that is able to perform slot tagging with no human intervention. This tagger is trained solely on the outputs of our method and thus does not rely on any labeled data. Our model demonstrates state-of-the-art performance in slot tagging without labeled training data on four different dialogue domains. Moreover, we find that slot annotations discovered by our model significantly improve the performance of an end-to-end dialogue response generation model, compared to using no slot annotation at all.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing

ISBN

978-1-954085-52-7

ISSN

—

e-ISSN

—

Počet stran výsledku

13

Strana od-do

2430-2442

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Online

Datum konání akce

2. 8. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—