@inproceedings{inoue-etal-2022-enhance,
title = "Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation",
author = "Inoue, Shumpei and
Liu, Tsungwei and
Nguyen, Son and
Nguyen, Minh-Tien",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.229",
doi = "10.18653/v1/2022.naacl-main.229",
pages = "3149--3158",
abstract = "This paper introduces a model for incomplete utterance restoration (IUR) called JET (Joint learning token Extraction and Text generation). Different from prior studies that only work on extraction or abstraction datasets, we design a simple but effective model, working for both scenarios of IUR. Our design simulates the nature of IUR, where omitted tokens from the context contribute to restoration. From this, we construct a Picker that identifies the omitted tokens. To support the picker, we design two label creation methods (soft and hard labels), which can work in cases of no annotation data for the omitted tokens. The restoration is done by using a Generator with the help of the Picker on joint learning. Promising results on four benchmark datasets in extraction and abstraction scenarios show that our model is better than the pretrained T5 and non-generative language model methods in both rich and limited training data settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="inoue-etal-2022-enhance">
<titleInfo>
<title>Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shumpei</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsungwei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Son</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh-Tien</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a model for incomplete utterance restoration (IUR) called JET (Joint learning token Extraction and Text generation). Different from prior studies that only work on extraction or abstraction datasets, we design a simple but effective model, working for both scenarios of IUR. Our design simulates the nature of IUR, where omitted tokens from the context contribute to restoration. From this, we construct a Picker that identifies the omitted tokens. To support the picker, we design two label creation methods (soft and hard labels), which can work in cases of no annotation data for the omitted tokens. The restoration is done by using a Generator with the help of the Picker on joint learning. Promising results on four benchmark datasets in extraction and abstraction scenarios show that our model is better than the pretrained T5 and non-generative language model methods in both rich and limited training data settings.</abstract>
<identifier type="citekey">inoue-etal-2022-enhance</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.229</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.229</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3149</start>
<end>3158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation
%A Inoue, Shumpei
%A Liu, Tsungwei
%A Nguyen, Son
%A Nguyen, Minh-Tien
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F inoue-etal-2022-enhance
%X This paper introduces a model for incomplete utterance restoration (IUR) called JET (Joint learning token Extraction and Text generation). Different from prior studies that only work on extraction or abstraction datasets, we design a simple but effective model, working for both scenarios of IUR. Our design simulates the nature of IUR, where omitted tokens from the context contribute to restoration. From this, we construct a Picker that identifies the omitted tokens. To support the picker, we design two label creation methods (soft and hard labels), which can work in cases of no annotation data for the omitted tokens. The restoration is done by using a Generator with the help of the Picker on joint learning. Promising results on four benchmark datasets in extraction and abstraction scenarios show that our model is better than the pretrained T5 and non-generative language model methods in both rich and limited training data settings.
%R 10.18653/v1/2022.naacl-main.229
%U https://aclanthology.org/2022.naacl-main.229
%U https://doi.org/10.18653/v1/2022.naacl-main.229
%P 3149-3158
Markdown (Informal)
[Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation](https://aclanthology.org/2022.naacl-main.229) (Inoue et al., NAACL 2022)
ACL