@inproceedings{zhao-yoshida-2022-simple,
title = "A Simple Yet Effective Hybrid Pre-trained Language Model for Unsupervised Sentence Acceptability Prediction",
author = "Zhao, Yang and
Yoshida, Issei",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.25",
pages = "194--201",
abstract = "Sentence acceptability judgment assesses to what degree a sentence is acceptable to native speakers of the language. Most unsupervised prediction approaches rely on a language model to obtain the likelihood of a sentence that reflects acceptability. However, two problems exist: first, low-frequency words would have a significant negative impact on the sentence likelihood derived from the language model; second, when it comes to multiple domains, the language model needs to be trained on domain-specific text for domain adaptation. To address both problems, we propose a simple method that substitutes Part-of-Speech (POS) tags for low-frequency words in sentences used for continual training of masked language models. Experimental results show that our word-tag-hybrid BERT model brings improvement on both a sentence acceptability benchmark and a cross-domain sentence acceptability evaluation corpus. Furthermore, our annotated cross-domain sentence acceptability evaluation corpus would benefit future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-yoshida-2022-simple">
<titleInfo>
<title>A Simple Yet Effective Hybrid Pre-trained Language Model for Unsupervised Sentence Acceptability Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Issei</namePart>
<namePart type="family">Yoshida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentence acceptability judgment assesses to what degree a sentence is acceptable to native speakers of the language. Most unsupervised prediction approaches rely on a language model to obtain the likelihood of a sentence that reflects acceptability. However, two problems exist: first, low-frequency words would have a significant negative impact on the sentence likelihood derived from the language model; second, when it comes to multiple domains, the language model needs to be trained on domain-specific text for domain adaptation. To address both problems, we propose a simple method that substitutes Part-of-Speech (POS) tags for low-frequency words in sentences used for continual training of masked language models. Experimental results show that our word-tag-hybrid BERT model brings improvement on both a sentence acceptability benchmark and a cross-domain sentence acceptability evaluation corpus. Furthermore, our annotated cross-domain sentence acceptability evaluation corpus would benefit future research.</abstract>
<identifier type="citekey">zhao-yoshida-2022-simple</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.25</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>194</start>
<end>201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simple Yet Effective Hybrid Pre-trained Language Model for Unsupervised Sentence Acceptability Prediction
%A Zhao, Yang
%A Yoshida, Issei
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F zhao-yoshida-2022-simple
%X Sentence acceptability judgment assesses to what degree a sentence is acceptable to native speakers of the language. Most unsupervised prediction approaches rely on a language model to obtain the likelihood of a sentence that reflects acceptability. However, two problems exist: first, low-frequency words would have a significant negative impact on the sentence likelihood derived from the language model; second, when it comes to multiple domains, the language model needs to be trained on domain-specific text for domain adaptation. To address both problems, we propose a simple method that substitutes Part-of-Speech (POS) tags for low-frequency words in sentences used for continual training of masked language models. Experimental results show that our word-tag-hybrid BERT model brings improvement on both a sentence acceptability benchmark and a cross-domain sentence acceptability evaluation corpus. Furthermore, our annotated cross-domain sentence acceptability evaluation corpus would benefit future research.
%U https://aclanthology.org/2022.aacl-short.25
%P 194-201
Markdown (Informal)
[A Simple Yet Effective Hybrid Pre-trained Language Model for Unsupervised Sentence Acceptability Prediction](https://aclanthology.org/2022.aacl-short.25) (Zhao & Yoshida, AACL-IJCNLP 2022)
ACL