@inproceedings{wu-etal-2021-spoken,
title = "Spoken Language Understanding for Task-oriented Dialogue Systems with Augmented Memory Networks",
author = "Wu, Jie and
Harris, Ian and
Zhao, Hongzhi",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.63",
doi = "10.18653/v1/2021.naacl-main.63",
pages = "797--806",
abstract = "Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot filling and intent detection are sharing semantic knowledge. Furthermore, attention mechanism boosts joint learning to achieve state-of-the-art results. However, current joint learning models ignore the following important facts: 1. Long-term slot context is not traced effectively, which is crucial for future slot filling. 2. Slot tagging and intent detection could be mutually rewarding, but bi-directional interaction between slot filling and intent detection remains seldom explored. In this paper, we propose a novel approach to model long-term slot context and to fully utilize the semantic correlation between slots and intents. We adopt a key-value memory network to model slot context dynamically and to track more important slot tags decoded before, which are then fed into our decoder for slot tagging. Furthermore, gated memory information is utilized to perform intent detection, mutually improving both tasks through global optimization. Experiments on benchmark ATIS and Snips datasets show that our model achieves state-of-the-art performance and outperforms other methods, especially for the slot filling task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2021-spoken">
<titleInfo>
<title>Spoken Language Understanding for Task-oriented Dialogue Systems with Augmented Memory Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Harris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhi</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot filling and intent detection are sharing semantic knowledge. Furthermore, attention mechanism boosts joint learning to achieve state-of-the-art results. However, current joint learning models ignore the following important facts: 1. Long-term slot context is not traced effectively, which is crucial for future slot filling. 2. Slot tagging and intent detection could be mutually rewarding, but bi-directional interaction between slot filling and intent detection remains seldom explored. In this paper, we propose a novel approach to model long-term slot context and to fully utilize the semantic correlation between slots and intents. We adopt a key-value memory network to model slot context dynamically and to track more important slot tags decoded before, which are then fed into our decoder for slot tagging. Furthermore, gated memory information is utilized to perform intent detection, mutually improving both tasks through global optimization. Experiments on benchmark ATIS and Snips datasets show that our model achieves state-of-the-art performance and outperforms other methods, especially for the slot filling task.</abstract>
<identifier type="citekey">wu-etal-2021-spoken</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.63</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.63</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>797</start>
<end>806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spoken Language Understanding for Task-oriented Dialogue Systems with Augmented Memory Networks
%A Wu, Jie
%A Harris, Ian
%A Zhao, Hongzhi
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F wu-etal-2021-spoken
%X Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot filling and intent detection are sharing semantic knowledge. Furthermore, attention mechanism boosts joint learning to achieve state-of-the-art results. However, current joint learning models ignore the following important facts: 1. Long-term slot context is not traced effectively, which is crucial for future slot filling. 2. Slot tagging and intent detection could be mutually rewarding, but bi-directional interaction between slot filling and intent detection remains seldom explored. In this paper, we propose a novel approach to model long-term slot context and to fully utilize the semantic correlation between slots and intents. We adopt a key-value memory network to model slot context dynamically and to track more important slot tags decoded before, which are then fed into our decoder for slot tagging. Furthermore, gated memory information is utilized to perform intent detection, mutually improving both tasks through global optimization. Experiments on benchmark ATIS and Snips datasets show that our model achieves state-of-the-art performance and outperforms other methods, especially for the slot filling task.
%R 10.18653/v1/2021.naacl-main.63
%U https://aclanthology.org/2021.naacl-main.63
%U https://doi.org/10.18653/v1/2021.naacl-main.63
%P 797-806
Markdown (Informal)
[Spoken Language Understanding for Task-oriented Dialogue Systems with Augmented Memory Networks](https://aclanthology.org/2021.naacl-main.63) (Wu et al., NAACL 2021)
ACL