@inproceedings{pouran-ben-veyseh-etal-2022-generating,
title = "Generating Complement Data for Aspect Term Extraction with {GPT}-2",
author = "Pouran Ben Veyseh, Amir and
Dernoncourt, Franck and
Min, Bonan and
Nguyen, Thien Huu",
editor = "Cherry, Colin and
Fan, Angela and
Foster, George and
Haffari, Gholamreza (Reza) and
Khadivi, Shahram and
Peng, Nanyun (Violet) and
Ren, Xiang and
Shareghi, Ehsan and
Swayamdipta, Swabha",
booktitle = "Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing",
month = jul,
year = "2022",
address = "Hybrid",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.deeplo-1.21",
doi = "10.18653/v1/2022.deeplo-1.21",
pages = "203--213",
abstract = "Aspect Term Extraction (ATE) is the task of identifying the word(s) in a review text toward which the author express an opinion. A major challenges for ATE involve data scarcity that hinder the training of deep sequence taggers to identify rare targets. To overcome these issues, we propose a novel method to better exploit the available labeled data for ATE by computing effective complement sentences to augment the input data and facilitate the aspect term prediction. In particular, we introduce a multistep training procedure that first obtains optimal complement representations and sentences for training data with respect to a deep ATE model. Afterward, we fine-tune the generative language model GPT-2 to allow complement sentence generation at test data. The REINFORCE algorithm is employed to incorporate different expected properties into the reward function to perform the fine-tuning. We perform extensive experiments on the benchmark datasets to demonstrate the benefits of the proposed method that achieve the state-of-the-art performance on different datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pouran-ben-veyseh-etal-2022-generating">
<titleInfo>
<title>Generating Complement Data for Aspect Term Extraction with GPT-2</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Pouran Ben Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</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 Third Workshop on Deep Learning for Low-Resource Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="given">(Reza)</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="given">(Violet)</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Aspect Term Extraction (ATE) is the task of identifying the word(s) in a review text toward which the author express an opinion. A major challenges for ATE involve data scarcity that hinder the training of deep sequence taggers to identify rare targets. To overcome these issues, we propose a novel method to better exploit the available labeled data for ATE by computing effective complement sentences to augment the input data and facilitate the aspect term prediction. In particular, we introduce a multistep training procedure that first obtains optimal complement representations and sentences for training data with respect to a deep ATE model. Afterward, we fine-tune the generative language model GPT-2 to allow complement sentence generation at test data. The REINFORCE algorithm is employed to incorporate different expected properties into the reward function to perform the fine-tuning. We perform extensive experiments on the benchmark datasets to demonstrate the benefits of the proposed method that achieve the state-of-the-art performance on different datasets.</abstract>
<identifier type="citekey">pouran-ben-veyseh-etal-2022-generating</identifier>
<identifier type="doi">10.18653/v1/2022.deeplo-1.21</identifier>
<location>
<url>https://aclanthology.org/2022.deeplo-1.21</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>203</start>
<end>213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Complement Data for Aspect Term Extraction with GPT-2
%A Pouran Ben Veyseh, Amir
%A Dernoncourt, Franck
%A Min, Bonan
%A Nguyen, Thien Huu
%Y Cherry, Colin
%Y Fan, Angela
%Y Foster, George
%Y Haffari, Gholamreza (Reza)
%Y Khadivi, Shahram
%Y Peng, Nanyun (Violet)
%Y Ren, Xiang
%Y Shareghi, Ehsan
%Y Swayamdipta, Swabha
%S Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid
%F pouran-ben-veyseh-etal-2022-generating
%X Aspect Term Extraction (ATE) is the task of identifying the word(s) in a review text toward which the author express an opinion. A major challenges for ATE involve data scarcity that hinder the training of deep sequence taggers to identify rare targets. To overcome these issues, we propose a novel method to better exploit the available labeled data for ATE by computing effective complement sentences to augment the input data and facilitate the aspect term prediction. In particular, we introduce a multistep training procedure that first obtains optimal complement representations and sentences for training data with respect to a deep ATE model. Afterward, we fine-tune the generative language model GPT-2 to allow complement sentence generation at test data. The REINFORCE algorithm is employed to incorporate different expected properties into the reward function to perform the fine-tuning. We perform extensive experiments on the benchmark datasets to demonstrate the benefits of the proposed method that achieve the state-of-the-art performance on different datasets.
%R 10.18653/v1/2022.deeplo-1.21
%U https://aclanthology.org/2022.deeplo-1.21
%U https://doi.org/10.18653/v1/2022.deeplo-1.21
%P 203-213
Markdown (Informal)
[Generating Complement Data for Aspect Term Extraction with GPT-2](https://aclanthology.org/2022.deeplo-1.21) (Pouran Ben Veyseh et al., DeepLo 2022)
ACL