@inproceedings{ohsugi-etal-2019-simple,
title = "A Simple but Effective Method to Incorporate Multi-turn Context with {BERT} for Conversational Machine Comprehension",
author = "Ohsugi, Yasuhito and
Saito, Itsumi and
Nishida, Kyosuke and
Asano, Hisako and
Tomita, Junji",
editor = "Chen, Yun-Nung and
Bedrax-Weiss, Tania and
Hakkani-Tur, Dilek and
Kumar, Anuj and
Lewis, Mike and
Luong, Thang-Minh and
Su, Pei-Hao and
Wen, Tsung-Hsien",
booktitle = "Proceedings of the First Workshop on NLP for Conversational AI",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4102",
doi = "10.18653/v1/W19-4102",
pages = "11--17",
abstract = "Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue. Using BERT, a pretraining language model, has been successful for single-turn machine comprehension, while modeling multiple turns of question answering with BERT has not been established because BERT has a limit on the number and the length of input sequences. In this paper, we propose a simple but effective method with BERT for CMC. Our method uses BERT to encode a paragraph independently conditioned with each question and each answer in a multi-turn context. Then, the method predicts an answer on the basis of the paragraph representations encoded with BERT. The experiments with representative CMC datasets, QuAC and CoQA, show that our method outperformed recently published methods (+0.8 F1 on QuAC and +2.1 F1 on CoQA). In addition, we conducted a detailed analysis of the effects of the number and types of dialogue history on the accuracy of CMC, and we found that the gold answer history, which may not be given in an actual conversation, contributed to the model performance most on both datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ohsugi-etal-2019-simple">
<titleInfo>
<title>A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yasuhito</namePart>
<namePart type="family">Ohsugi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itsumi</namePart>
<namePart type="family">Saito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyosuke</namePart>
<namePart type="family">Nishida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hisako</namePart>
<namePart type="family">Asano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junji</namePart>
<namePart type="family">Tomita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on NLP for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tania</namePart>
<namePart type="family">Bedrax-Weiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thang-Minh</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei-Hao</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue. Using BERT, a pretraining language model, has been successful for single-turn machine comprehension, while modeling multiple turns of question answering with BERT has not been established because BERT has a limit on the number and the length of input sequences. In this paper, we propose a simple but effective method with BERT for CMC. Our method uses BERT to encode a paragraph independently conditioned with each question and each answer in a multi-turn context. Then, the method predicts an answer on the basis of the paragraph representations encoded with BERT. The experiments with representative CMC datasets, QuAC and CoQA, show that our method outperformed recently published methods (+0.8 F1 on QuAC and +2.1 F1 on CoQA). In addition, we conducted a detailed analysis of the effects of the number and types of dialogue history on the accuracy of CMC, and we found that the gold answer history, which may not be given in an actual conversation, contributed to the model performance most on both datasets.</abstract>
<identifier type="citekey">ohsugi-etal-2019-simple</identifier>
<identifier type="doi">10.18653/v1/W19-4102</identifier>
<location>
<url>https://aclanthology.org/W19-4102</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>11</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension
%A Ohsugi, Yasuhito
%A Saito, Itsumi
%A Nishida, Kyosuke
%A Asano, Hisako
%A Tomita, Junji
%Y Chen, Yun-Nung
%Y Bedrax-Weiss, Tania
%Y Hakkani-Tur, Dilek
%Y Kumar, Anuj
%Y Lewis, Mike
%Y Luong, Thang-Minh
%Y Su, Pei-Hao
%Y Wen, Tsung-Hsien
%S Proceedings of the First Workshop on NLP for Conversational AI
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F ohsugi-etal-2019-simple
%X Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue. Using BERT, a pretraining language model, has been successful for single-turn machine comprehension, while modeling multiple turns of question answering with BERT has not been established because BERT has a limit on the number and the length of input sequences. In this paper, we propose a simple but effective method with BERT for CMC. Our method uses BERT to encode a paragraph independently conditioned with each question and each answer in a multi-turn context. Then, the method predicts an answer on the basis of the paragraph representations encoded with BERT. The experiments with representative CMC datasets, QuAC and CoQA, show that our method outperformed recently published methods (+0.8 F1 on QuAC and +2.1 F1 on CoQA). In addition, we conducted a detailed analysis of the effects of the number and types of dialogue history on the accuracy of CMC, and we found that the gold answer history, which may not be given in an actual conversation, contributed to the model performance most on both datasets.
%R 10.18653/v1/W19-4102
%U https://aclanthology.org/W19-4102
%U https://doi.org/10.18653/v1/W19-4102
%P 11-17
Markdown (Informal)
[A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension](https://aclanthology.org/W19-4102) (Ohsugi et al., ACL 2019)
ACL