@inproceedings{gu-yu-2020-data,
title = "{D}ata {A}nnealing for {I}nformal {L}anguage {U}nderstanding {T}asks",
author = "Gu, Jing and
Yu, Zhou",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.282",
doi = "10.18653/v1/2020.findings-emnlp.282",
pages = "3153--3159",
abstract = "There is a huge performance gap between formal and informal language understanding tasks. The recent pre-trained models that improved formal language understanding tasks did not achieve a comparable result on informal language. We propose data annealing transfer learning procedure to bridge the performance gap on informal natural language understanding tasks. It successfully utilizes a pre-trained model such as BERT in informal language. In the data annealing procedure, the training set contains mainly formal text data at first; then, the proportion of the informal text data is gradually increased during the training process. Our data annealing procedure is model-independent and can be applied to various tasks. We validate its effectiveness in exhaustive experiments. When BERT is implemented with our learning procedure, it outperforms all the state-of-the-art models on the three common informal language tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-yu-2020-data">
<titleInfo>
<title>Data Annealing for Informal Language Understanding Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Yang</namePart>
<namePart type="family">Liu</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>There is a huge performance gap between formal and informal language understanding tasks. The recent pre-trained models that improved formal language understanding tasks did not achieve a comparable result on informal language. We propose data annealing transfer learning procedure to bridge the performance gap on informal natural language understanding tasks. It successfully utilizes a pre-trained model such as BERT in informal language. In the data annealing procedure, the training set contains mainly formal text data at first; then, the proportion of the informal text data is gradually increased during the training process. Our data annealing procedure is model-independent and can be applied to various tasks. We validate its effectiveness in exhaustive experiments. When BERT is implemented with our learning procedure, it outperforms all the state-of-the-art models on the three common informal language tasks.</abstract>
<identifier type="citekey">gu-yu-2020-data</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.282</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.282</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3153</start>
<end>3159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Annealing for Informal Language Understanding Tasks
%A Gu, Jing
%A Yu, Zhou
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F gu-yu-2020-data
%X There is a huge performance gap between formal and informal language understanding tasks. The recent pre-trained models that improved formal language understanding tasks did not achieve a comparable result on informal language. We propose data annealing transfer learning procedure to bridge the performance gap on informal natural language understanding tasks. It successfully utilizes a pre-trained model such as BERT in informal language. In the data annealing procedure, the training set contains mainly formal text data at first; then, the proportion of the informal text data is gradually increased during the training process. Our data annealing procedure is model-independent and can be applied to various tasks. We validate its effectiveness in exhaustive experiments. When BERT is implemented with our learning procedure, it outperforms all the state-of-the-art models on the three common informal language tasks.
%R 10.18653/v1/2020.findings-emnlp.282
%U https://aclanthology.org/2020.findings-emnlp.282
%U https://doi.org/10.18653/v1/2020.findings-emnlp.282
%P 3153-3159
Markdown (Informal)
[Data Annealing for Informal Language Understanding Tasks](https://aclanthology.org/2020.findings-emnlp.282) (Gu & Yu, Findings 2020)
ACL