@inproceedings{liu-yu-2019-blcu,
title = "{BLCU}-{NLP} at {COIN}-Shared Task1: Stagewise Fine-tuning {BERT} for Commonsense Inference in Everyday Narrations",
author = "Liu, Chunhua and
Yu, Dong",
editor = "Ostermann, Simon and
Zhang, Sheng and
Roth, Michael and
Clark, Peter",
booktitle = "Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6012",
doi = "10.18653/v1/D19-6012",
pages = "99--103",
abstract = "This paper describes our system for COIN Shared Task 1: Commonsense Inference in Everyday Narrations. To inject more external knowledge to better reason over the narrative passage, question and answer, the system adopts a stagewise fine-tuning method based on pre-trained BERT model. More specifically, the first stage is to fine-tune on addi- tional machine reading comprehension dataset to learn more commonsense knowledge. The second stage is to fine-tune on target-task (MCScript2.0) with MCScript (2018) dataset assisted. Experimental results show that our system achieves significant improvements over the baseline systems with 84.2{\%} accuracy on the official test dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-yu-2019-blcu">
<titleInfo>
<title>BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chunhua</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Yu</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 First Workshop on Commonsense Inference in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Ostermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Clark</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>This paper describes our system for COIN Shared Task 1: Commonsense Inference in Everyday Narrations. To inject more external knowledge to better reason over the narrative passage, question and answer, the system adopts a stagewise fine-tuning method based on pre-trained BERT model. More specifically, the first stage is to fine-tune on addi- tional machine reading comprehension dataset to learn more commonsense knowledge. The second stage is to fine-tune on target-task (MCScript2.0) with MCScript (2018) dataset assisted. Experimental results show that our system achieves significant improvements over the baseline systems with 84.2% accuracy on the official test dataset.</abstract>
<identifier type="citekey">liu-yu-2019-blcu</identifier>
<identifier type="doi">10.18653/v1/D19-6012</identifier>
<location>
<url>https://aclanthology.org/D19-6012</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>99</start>
<end>103</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations
%A Liu, Chunhua
%A Yu, Dong
%Y Ostermann, Simon
%Y Zhang, Sheng
%Y Roth, Michael
%Y Clark, Peter
%S Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F liu-yu-2019-blcu
%X This paper describes our system for COIN Shared Task 1: Commonsense Inference in Everyday Narrations. To inject more external knowledge to better reason over the narrative passage, question and answer, the system adopts a stagewise fine-tuning method based on pre-trained BERT model. More specifically, the first stage is to fine-tune on addi- tional machine reading comprehension dataset to learn more commonsense knowledge. The second stage is to fine-tune on target-task (MCScript2.0) with MCScript (2018) dataset assisted. Experimental results show that our system achieves significant improvements over the baseline systems with 84.2% accuracy on the official test dataset.
%R 10.18653/v1/D19-6012
%U https://aclanthology.org/D19-6012
%U https://doi.org/10.18653/v1/D19-6012
%P 99-103
Markdown (Informal)
[BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations](https://aclanthology.org/D19-6012) (Liu & Yu, 2019)
ACL