@inproceedings{koreeda-etal-2019-hitachi,
title = "Hitachi at {MRP} 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing",
author = "Koreeda, Yuta and
Morio, Gaku and
Morishita, Terufumi and
Ozaki, Hiroaki and
Yanai, Kohsuke",
editor = "Oepen, Stephan and
Abend, Omri and
Hajic, Jan and
Hershcovich, Daniel and
Kuhlmann, Marco and
O{'}Gorman, Tim and
Xue, Nianwen",
booktitle = "Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-2011",
doi = "10.18653/v1/K19-2011",
pages = "114--126",
abstract = "This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task. In this shared task, the participating systems were asked to predict nodes, edges and their attributes for five frameworks, each with different order of {``}abstraction{''} from input tokens. We proposed a unified encoder-to-biaffine network for all five frameworks, which effectively incorporates a shared encoder to extract rich input features, decoder networks to generate anchorless nodes in UCCA and AMR, and biaffine networks to predict edges. Our system was ranked fifth with the macro-averaged MRP F1 score of 0.7604, and outperformed the baseline unified transition-based MRP. Furthermore, post-evaluation experiments showed that we can boost the performance of the proposed system by incorporating multi-task learning, whereas the baseline could not. These imply efficacy of incorporating the biaffine network to the shared architecture for MRP and that learning heterogeneous meaning representations at once can boost the system performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koreeda-etal-2019-hitachi">
<titleInfo>
<title>Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Koreeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terufumi</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Ozaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kohsuke</namePart>
<namePart type="family">Yanai</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 Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Oepen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Hajic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Kuhlmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">O’Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task. In this shared task, the participating systems were asked to predict nodes, edges and their attributes for five frameworks, each with different order of “abstraction” from input tokens. We proposed a unified encoder-to-biaffine network for all five frameworks, which effectively incorporates a shared encoder to extract rich input features, decoder networks to generate anchorless nodes in UCCA and AMR, and biaffine networks to predict edges. Our system was ranked fifth with the macro-averaged MRP F1 score of 0.7604, and outperformed the baseline unified transition-based MRP. Furthermore, post-evaluation experiments showed that we can boost the performance of the proposed system by incorporating multi-task learning, whereas the baseline could not. These imply efficacy of incorporating the biaffine network to the shared architecture for MRP and that learning heterogeneous meaning representations at once can boost the system performance.</abstract>
<identifier type="citekey">koreeda-etal-2019-hitachi</identifier>
<identifier type="doi">10.18653/v1/K19-2011</identifier>
<location>
<url>https://aclanthology.org/K19-2011</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>114</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing
%A Koreeda, Yuta
%A Morio, Gaku
%A Morishita, Terufumi
%A Ozaki, Hiroaki
%A Yanai, Kohsuke
%Y Oepen, Stephan
%Y Abend, Omri
%Y Hajic, Jan
%Y Hershcovich, Daniel
%Y Kuhlmann, Marco
%Y O’Gorman, Tim
%Y Xue, Nianwen
%S Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F koreeda-etal-2019-hitachi
%X This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task. In this shared task, the participating systems were asked to predict nodes, edges and their attributes for five frameworks, each with different order of “abstraction” from input tokens. We proposed a unified encoder-to-biaffine network for all five frameworks, which effectively incorporates a shared encoder to extract rich input features, decoder networks to generate anchorless nodes in UCCA and AMR, and biaffine networks to predict edges. Our system was ranked fifth with the macro-averaged MRP F1 score of 0.7604, and outperformed the baseline unified transition-based MRP. Furthermore, post-evaluation experiments showed that we can boost the performance of the proposed system by incorporating multi-task learning, whereas the baseline could not. These imply efficacy of incorporating the biaffine network to the shared architecture for MRP and that learning heterogeneous meaning representations at once can boost the system performance.
%R 10.18653/v1/K19-2011
%U https://aclanthology.org/K19-2011
%U https://doi.org/10.18653/v1/K19-2011
%P 114-126
Markdown (Informal)
[Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing](https://aclanthology.org/K19-2011) (Koreeda et al., CoNLL 2019)
ACL