@inproceedings{casanueva-etal-2020-efficient,
title = "Efficient Intent Detection with Dual Sentence Encoders",
author = "Casanueva, I{\~n}igo and
Tem{\v{c}}inas, Tadas and
Gerz, Daniela and
Henderson, Matthew and
Vuli{\'c}, Ivan",
editor = "Wen, Tsung-Hsien and
Celikyilmaz, Asli and
Yu, Zhou and
Papangelis, Alexandros and
Eric, Mihail and
Kumar, Anuj and
Casanueva, I{\~n}igo and
Shah, Rushin",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlp4convai-1.5",
doi = "10.18653/v1/2020.nlp4convai-1.5",
pages = "38--45",
abstract = "Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that: 1) they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets; 2) the gains are especially pronounced in few-shot setups (i.e., with only 10 or 30 annotated examples per intent); 3) our intent detectors can be trained in a matter of minutes on a single CPU; and 4) they are stable across different hyperparameter settings. In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="casanueva-etal-2020-efficient">
<titleInfo>
<title>Efficient Intent Detection with Dual Sentence Encoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iñigo</namePart>
<namePart type="family">Casanueva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadas</namePart>
<namePart type="family">Temčinas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Gerz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Henderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihail</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñigo</namePart>
<namePart type="family">Casanueva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rushin</namePart>
<namePart type="family">Shah</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>Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that: 1) they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets; 2) the gains are especially pronounced in few-shot setups (i.e., with only 10 or 30 annotated examples per intent); 3) our intent detectors can be trained in a matter of minutes on a single CPU; and 4) they are stable across different hyperparameter settings. In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.</abstract>
<identifier type="citekey">casanueva-etal-2020-efficient</identifier>
<identifier type="doi">10.18653/v1/2020.nlp4convai-1.5</identifier>
<location>
<url>https://aclanthology.org/2020.nlp4convai-1.5</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>38</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Intent Detection with Dual Sentence Encoders
%A Casanueva, Iñigo
%A Temčinas, Tadas
%A Gerz, Daniela
%A Henderson, Matthew
%A Vulić, Ivan
%Y Wen, Tsung-Hsien
%Y Celikyilmaz, Asli
%Y Yu, Zhou
%Y Papangelis, Alexandros
%Y Eric, Mihail
%Y Kumar, Anuj
%Y Casanueva, Iñigo
%Y Shah, Rushin
%S Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F casanueva-etal-2020-efficient
%X Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that: 1) they outperform intent detectors based on fine-tuning the full BERT-Large model or using BERT as a fixed black-box encoder on three diverse intent detection data sets; 2) the gains are especially pronounced in few-shot setups (i.e., with only 10 or 30 annotated examples per intent); 3) our intent detectors can be trained in a matter of minutes on a single CPU; and 4) they are stable across different hyperparameter settings. In hope of facilitating and democratizing research focused on intention detection, we release our code, as well as a new challenging single-domain intent detection dataset comprising 13,083 annotated examples over 77 intents.
%R 10.18653/v1/2020.nlp4convai-1.5
%U https://aclanthology.org/2020.nlp4convai-1.5
%U https://doi.org/10.18653/v1/2020.nlp4convai-1.5
%P 38-45
Markdown (Informal)
[Efficient Intent Detection with Dual Sentence Encoders](https://aclanthology.org/2020.nlp4convai-1.5) (Casanueva et al., NLP4ConvAI 2020)
ACL
- Iñigo Casanueva, Tadas Temčinas, Daniela Gerz, Matthew Henderson, and Ivan Vulić. 2020. Efficient Intent Detection with Dual Sentence Encoders. In Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, pages 38–45, Online. Association for Computational Linguistics.