@inproceedings{yolchuyeva-etal-2019-self,
title = "Self-Attention Networks for Intent Detection",
author = "Yolchuyeva, Sevinj and
N{\'e}meth, G{\'e}za and
Gyires-T{\'o}th, B{\'a}lint",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-1157",
doi = "10.26615/978-954-452-056-4_157",
pages = "1373--1379",
abstract = "Self-attention networks (SAN) have shown promising performance in various Natural Language Processing (NLP) scenarios, especially in machine translation. One of the main points of SANs is the strength of capturing long-range and multi-scale dependencies from the data. In this paper, we present a novel intent detection system which is based on a self-attention network and a Bi-LSTM. Our approach shows improvement by using a transformer model and deep averaging network-based universal sentence encoder compared to previous solutions. We evaluate the system on Snips, Smart Speaker, Smart Lights, and ATIS datasets by different evaluation metrics. The performance of the proposed model is compared with LSTM with the same datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yolchuyeva-etal-2019-self">
<titleInfo>
<title>Self-Attention Networks for Intent Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sevinj</namePart>
<namePart type="family">Yolchuyeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Géza</namePart>
<namePart type="family">Németh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bálint</namePart>
<namePart type="family">Gyires-Tóth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Self-attention networks (SAN) have shown promising performance in various Natural Language Processing (NLP) scenarios, especially in machine translation. One of the main points of SANs is the strength of capturing long-range and multi-scale dependencies from the data. In this paper, we present a novel intent detection system which is based on a self-attention network and a Bi-LSTM. Our approach shows improvement by using a transformer model and deep averaging network-based universal sentence encoder compared to previous solutions. We evaluate the system on Snips, Smart Speaker, Smart Lights, and ATIS datasets by different evaluation metrics. The performance of the proposed model is compared with LSTM with the same datasets.</abstract>
<identifier type="citekey">yolchuyeva-etal-2019-self</identifier>
<identifier type="doi">10.26615/978-954-452-056-4_157</identifier>
<location>
<url>https://aclanthology.org/R19-1157</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>1373</start>
<end>1379</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Attention Networks for Intent Detection
%A Yolchuyeva, Sevinj
%A Németh, Géza
%A Gyires-Tóth, Bálint
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F yolchuyeva-etal-2019-self
%X Self-attention networks (SAN) have shown promising performance in various Natural Language Processing (NLP) scenarios, especially in machine translation. One of the main points of SANs is the strength of capturing long-range and multi-scale dependencies from the data. In this paper, we present a novel intent detection system which is based on a self-attention network and a Bi-LSTM. Our approach shows improvement by using a transformer model and deep averaging network-based universal sentence encoder compared to previous solutions. We evaluate the system on Snips, Smart Speaker, Smart Lights, and ATIS datasets by different evaluation metrics. The performance of the proposed model is compared with LSTM with the same datasets.
%R 10.26615/978-954-452-056-4_157
%U https://aclanthology.org/R19-1157
%U https://doi.org/10.26615/978-954-452-056-4_157
%P 1373-1379
Markdown (Informal)
[Self-Attention Networks for Intent Detection](https://aclanthology.org/R19-1157) (Yolchuyeva et al., RANLP 2019)
ACL
- Sevinj Yolchuyeva, Géza Németh, and Bálint Gyires-Tóth. 2019. Self-Attention Networks for Intent Detection. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1373–1379, Varna, Bulgaria. INCOMA Ltd..