@inproceedings{de-kok-etal-2017-pp,
title = "{PP} Attachment: Where do We Stand?",
author = {de Kok, Dani{\"e}l and
Ma, Jianqiang and
Dima, Corina and
Hinrichs, Erhard},
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 2, Short Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-2050",
pages = "311--317",
abstract = "Prepostitional phrase (PP) attachment is a well known challenge to parsing. In this paper, we combine the insights of different works, namely: (1) treating PP attachment as a classification task with an arbitrary number of attachment candidates; (2) using auxiliary distributions to augment the data beyond the hand-annotated training set; (3) using topological fields to get information about the distribution of PP attachment throughout clauses and (4) using state-of-the-art techniques such as word embeddings and neural networks. We show that jointly using these techniques leads to substantial improvements. We also conduct a qualitative analysis to gauge where the ceiling of the task is in a realistic setup.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-kok-etal-2017-pp">
<titleInfo>
<title>PP Attachment: Where do We Stand?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniël</namePart>
<namePart type="family">de Kok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianqiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Corina</namePart>
<namePart type="family">Dima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erhard</namePart>
<namePart type="family">Hinrichs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prepostitional phrase (PP) attachment is a well known challenge to parsing. In this paper, we combine the insights of different works, namely: (1) treating PP attachment as a classification task with an arbitrary number of attachment candidates; (2) using auxiliary distributions to augment the data beyond the hand-annotated training set; (3) using topological fields to get information about the distribution of PP attachment throughout clauses and (4) using state-of-the-art techniques such as word embeddings and neural networks. We show that jointly using these techniques leads to substantial improvements. We also conduct a qualitative analysis to gauge where the ceiling of the task is in a realistic setup.</abstract>
<identifier type="citekey">de-kok-etal-2017-pp</identifier>
<location>
<url>https://aclanthology.org/E17-2050</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>311</start>
<end>317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PP Attachment: Where do We Stand?
%A de Kok, Daniël
%A Ma, Jianqiang
%A Dima, Corina
%A Hinrichs, Erhard
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F de-kok-etal-2017-pp
%X Prepostitional phrase (PP) attachment is a well known challenge to parsing. In this paper, we combine the insights of different works, namely: (1) treating PP attachment as a classification task with an arbitrary number of attachment candidates; (2) using auxiliary distributions to augment the data beyond the hand-annotated training set; (3) using topological fields to get information about the distribution of PP attachment throughout clauses and (4) using state-of-the-art techniques such as word embeddings and neural networks. We show that jointly using these techniques leads to substantial improvements. We also conduct a qualitative analysis to gauge where the ceiling of the task is in a realistic setup.
%U https://aclanthology.org/E17-2050
%P 311-317
Markdown (Informal)
[PP Attachment: Where do We Stand?](https://aclanthology.org/E17-2050) (de Kok et al., EACL 2017)
ACL
- Daniël de Kok, Jianqiang Ma, Corina Dima, and Erhard Hinrichs. 2017. PP Attachment: Where do We Stand?. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 311–317, Valencia, Spain. Association for Computational Linguistics.