@inproceedings{do-rehbein-2020-parsers,
title = "Parsers Know Best: {G}erman {PP} Attachment Revisited",
author = "Do, Bich-Ngoc and
Rehbein, Ines",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.185",
doi = "10.18653/v1/2020.coling-main.185",
pages = "2049--2061",
abstract = "In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system{'}s output to the output of a full syntactic parser leads to an overly optimistic assessment of the results. We address these issues by presenting a realistic evaluation of the potential of different PP attachment systems, using fully predicted information as system input. We compare our results against the output of a strong neural parser and show that the full parsing approach is superior to modeling PP attachment disambiguation as a separate task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-rehbein-2020-parsers">
<titleInfo>
<title>Parsers Know Best: German PP Attachment Revisited</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bich-Ngoc</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ines</namePart>
<namePart type="family">Rehbein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system’s output to the output of a full syntactic parser leads to an overly optimistic assessment of the results. We address these issues by presenting a realistic evaluation of the potential of different PP attachment systems, using fully predicted information as system input. We compare our results against the output of a strong neural parser and show that the full parsing approach is superior to modeling PP attachment disambiguation as a separate task.</abstract>
<identifier type="citekey">do-rehbein-2020-parsers</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.185</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.185</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2049</start>
<end>2061</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parsers Know Best: German PP Attachment Revisited
%A Do, Bich-Ngoc
%A Rehbein, Ines
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F do-rehbein-2020-parsers
%X In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system’s output to the output of a full syntactic parser leads to an overly optimistic assessment of the results. We address these issues by presenting a realistic evaluation of the potential of different PP attachment systems, using fully predicted information as system input. We compare our results against the output of a strong neural parser and show that the full parsing approach is superior to modeling PP attachment disambiguation as a separate task.
%R 10.18653/v1/2020.coling-main.185
%U https://aclanthology.org/2020.coling-main.185
%U https://doi.org/10.18653/v1/2020.coling-main.185
%P 2049-2061
Markdown (Informal)
[Parsers Know Best: German PP Attachment Revisited](https://aclanthology.org/2020.coling-main.185) (Do & Rehbein, COLING 2020)
ACL
- Bich-Ngoc Do and Ines Rehbein. 2020. Parsers Know Best: German PP Attachment Revisited. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2049–2061, Barcelona, Spain (Online). International Committee on Computational Linguistics.