@inproceedings{bao-etal-2019-inspecting,
title = "Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension",
author = "Bao, Hangbo and
Dong, Li and
Wei, Furu and
Wang, Wenhui and
Yang, Nan and
Cui, Lei and
Piao, Songhao and
Zhou, Ming",
editor = "Fisch, Adam and
Talmor, Alon and
Jia, Robin and
Seo, Minjoon and
Choi, Eunsol and
Chen, Danqi",
booktitle = "Proceedings of the 2nd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5802",
doi = "10.18653/v1/D19-5802",
pages = "14--18",
abstract = "Most machine reading comprehension (MRC) models separately handle encoding and matching with different network architectures. In contrast, pretrained language models with Transformer layers, such as GPT (Radford et al., 2018) and BERT (Devlin et al., 2018), have achieved competitive performance on MRC. A research question that naturally arises is: apart from the benefits of pre-training, how many performance gain comes from the unified network architecture. In this work, we evaluate and analyze unifying encoding and matching components with Transformer for the MRC task. Experimental results on SQuAD show that the unified model outperforms previous networks that separately treat encoding and matching. We also introduce a metric to inspect whether a Transformer layer tends to perform encoding or matching. The analysis results show that the unified model learns different modeling strategies compared with previous manually-designed models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2019-inspecting">
<titleInfo>
<title>Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hangbo</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songhao</namePart>
<namePart type="family">Piao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</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 2nd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Fisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Talmor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</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>Most machine reading comprehension (MRC) models separately handle encoding and matching with different network architectures. In contrast, pretrained language models with Transformer layers, such as GPT (Radford et al., 2018) and BERT (Devlin et al., 2018), have achieved competitive performance on MRC. A research question that naturally arises is: apart from the benefits of pre-training, how many performance gain comes from the unified network architecture. In this work, we evaluate and analyze unifying encoding and matching components with Transformer for the MRC task. Experimental results on SQuAD show that the unified model outperforms previous networks that separately treat encoding and matching. We also introduce a metric to inspect whether a Transformer layer tends to perform encoding or matching. The analysis results show that the unified model learns different modeling strategies compared with previous manually-designed models.</abstract>
<identifier type="citekey">bao-etal-2019-inspecting</identifier>
<identifier type="doi">10.18653/v1/D19-5802</identifier>
<location>
<url>https://aclanthology.org/D19-5802</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>14</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension
%A Bao, Hangbo
%A Dong, Li
%A Wei, Furu
%A Wang, Wenhui
%A Yang, Nan
%A Cui, Lei
%A Piao, Songhao
%A Zhou, Ming
%Y Fisch, Adam
%Y Talmor, Alon
%Y Jia, Robin
%Y Seo, Minjoon
%Y Choi, Eunsol
%Y Chen, Danqi
%S Proceedings of the 2nd Workshop on Machine Reading for Question Answering
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F bao-etal-2019-inspecting
%X Most machine reading comprehension (MRC) models separately handle encoding and matching with different network architectures. In contrast, pretrained language models with Transformer layers, such as GPT (Radford et al., 2018) and BERT (Devlin et al., 2018), have achieved competitive performance on MRC. A research question that naturally arises is: apart from the benefits of pre-training, how many performance gain comes from the unified network architecture. In this work, we evaluate and analyze unifying encoding and matching components with Transformer for the MRC task. Experimental results on SQuAD show that the unified model outperforms previous networks that separately treat encoding and matching. We also introduce a metric to inspect whether a Transformer layer tends to perform encoding or matching. The analysis results show that the unified model learns different modeling strategies compared with previous manually-designed models.
%R 10.18653/v1/D19-5802
%U https://aclanthology.org/D19-5802
%U https://doi.org/10.18653/v1/D19-5802
%P 14-18
Markdown (Informal)
[Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension](https://aclanthology.org/D19-5802) (Bao et al., 2019)
ACL
- Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Lei Cui, Songhao Piao, and Ming Zhou. 2019. Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 14–18, Hong Kong, China. Association for Computational Linguistics.