@inproceedings{hudecek-etal-2021-discovering,
title = "Discovering Dialogue Slots with Weak Supervision",
author = "Hude{\v{c}}ek, Vojt{\v{e}}ch and
Du{\v{s}}ek, Ond{\v{r}}ej and
Yu, Zhou",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.189",
doi = "10.18653/v1/2021.acl-long.189",
pages = "2430--2442",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hudecek-etal-2021-discovering">
<titleInfo>
<title>Discovering Dialogue Slots with Weak Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vojtěch</namePart>
<namePart type="family">Hudeček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">hudecek-etal-2021-discovering</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.189</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.189</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2430</start>
<end>2442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discovering Dialogue Slots with Weak Supervision
%A Hudeček, Vojtěch
%A Dušek, Ondřej
%A Yu, Zhou
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F hudecek-etal-2021-discovering
%X 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.
%R 10.18653/v1/2021.acl-long.189
%U https://aclanthology.org/2021.acl-long.189
%U https://doi.org/10.18653/v1/2021.acl-long.189
%P 2430-2442
Markdown (Informal)
[Discovering Dialogue Slots with Weak Supervision](https://aclanthology.org/2021.acl-long.189) (Hudeček et al., ACL-IJCNLP 2021)
ACL
- Vojtěch Hudeček, Ondřej Dušek, and Zhou Yu. 2021. Discovering Dialogue Slots with Weak Supervision. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2430–2442, Online. Association for Computational Linguistics.