@inproceedings{sung-etal-2019-pre,
title = "Pre-Training {BERT} on Domain Resources for Short Answer Grading",
author = "Sung, Chul and
Dhamecha, Tejas and
Saha, Swarnadeep and
Ma, Tengfei and
Reddy, Vinay and
Arora, Rishi",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1628",
doi = "10.18653/v1/D19-1628",
pages = "6071--6075",
abstract = "Pre-trained BERT contextualized representations have achieved state-of-the-art results on multiple downstream NLP tasks by fine-tuning with task-specific data. While there has been a lot of focus on task-specific fine-tuning, there has been limited work on improving the pre-trained representations. In this paper, we explore ways of improving the pre-trained contextual representations for the task of automatic short answer grading, a critical component of intelligent tutoring systems. We show that the pre-trained BERT model can be improved by augmenting data from the domain-specific resources like textbooks. We also present a new approach to use labeled short answering grading data for further enhancement of the language model. Empirical evaluation on multi-domain datasets shows that task-specific fine-tuning on the enhanced pre-trained language model achieves superior performance for short answer grading.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-etal-2019-pre">
<titleInfo>
<title>Pre-Training BERT on Domain Resources for Short Answer Grading</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chul</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejas</namePart>
<namePart type="family">Dhamecha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swarnadeep</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tengfei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinay</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishi</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained BERT contextualized representations have achieved state-of-the-art results on multiple downstream NLP tasks by fine-tuning with task-specific data. While there has been a lot of focus on task-specific fine-tuning, there has been limited work on improving the pre-trained representations. In this paper, we explore ways of improving the pre-trained contextual representations for the task of automatic short answer grading, a critical component of intelligent tutoring systems. We show that the pre-trained BERT model can be improved by augmenting data from the domain-specific resources like textbooks. We also present a new approach to use labeled short answering grading data for further enhancement of the language model. Empirical evaluation on multi-domain datasets shows that task-specific fine-tuning on the enhanced pre-trained language model achieves superior performance for short answer grading.</abstract>
<identifier type="citekey">sung-etal-2019-pre</identifier>
<identifier type="doi">10.18653/v1/D19-1628</identifier>
<location>
<url>https://aclanthology.org/D19-1628</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>6071</start>
<end>6075</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-Training BERT on Domain Resources for Short Answer Grading
%A Sung, Chul
%A Dhamecha, Tejas
%A Saha, Swarnadeep
%A Ma, Tengfei
%A Reddy, Vinay
%A Arora, Rishi
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F sung-etal-2019-pre
%X Pre-trained BERT contextualized representations have achieved state-of-the-art results on multiple downstream NLP tasks by fine-tuning with task-specific data. While there has been a lot of focus on task-specific fine-tuning, there has been limited work on improving the pre-trained representations. In this paper, we explore ways of improving the pre-trained contextual representations for the task of automatic short answer grading, a critical component of intelligent tutoring systems. We show that the pre-trained BERT model can be improved by augmenting data from the domain-specific resources like textbooks. We also present a new approach to use labeled short answering grading data for further enhancement of the language model. Empirical evaluation on multi-domain datasets shows that task-specific fine-tuning on the enhanced pre-trained language model achieves superior performance for short answer grading.
%R 10.18653/v1/D19-1628
%U https://aclanthology.org/D19-1628
%U https://doi.org/10.18653/v1/D19-1628
%P 6071-6075
Markdown (Informal)
[Pre-Training BERT on Domain Resources for Short Answer Grading](https://aclanthology.org/D19-1628) (Sung et al., EMNLP-IJCNLP 2019)
ACL
- Chul Sung, Tejas Dhamecha, Swarnadeep Saha, Tengfei Ma, Vinay Reddy, and Rishi Arora. 2019. Pre-Training BERT on Domain Resources for Short Answer Grading. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6071–6075, Hong Kong, China. Association for Computational Linguistics.