@inproceedings{elkahky-etal-2018-challenge,
title = "A Challenge Set and Methods for Noun-Verb Ambiguity",
author = "Elkahky, Ali and
Webster, Kellie and
Andor, Daniel and
Pitler, Emily",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1277",
doi = "10.18653/v1/D18-1277",
pages = "2562--2572",
abstract = "English part-of-speech taggers regularly make egregious errors related to noun-verb ambiguity, despite having achieved 97{\%}+ accuracy on the WSJ Penn Treebank since 2002. These mistakes have been difficult to quantify and make taggers less useful to downstream tasks such as translation and text-to-speech synthesis. This paper creates a new dataset of over 30,000 naturally-occurring non-trivial examples of noun-verb ambiguity. Taggers within 1{\%} of each other when measured on the WSJ have accuracies ranging from 57{\%} to 75{\%} accuracy on this challenge set. Enhancing the strongest existing tagger with contextual word embeddings and targeted training data improves its accuracy to 89{\%}, a 14{\%} absolute (52{\%} relative) improvement. Downstream, using just this enhanced tagger yields a 28{\%} reduction in error over the prior best learned model for homograph disambiguation for textto-speech synthesis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elkahky-etal-2018-challenge">
<titleInfo>
<title>A Challenge Set and Methods for Noun-Verb Ambiguity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Elkahky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kellie</namePart>
<namePart type="family">Webster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Andor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Pitler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>English part-of-speech taggers regularly make egregious errors related to noun-verb ambiguity, despite having achieved 97%+ accuracy on the WSJ Penn Treebank since 2002. These mistakes have been difficult to quantify and make taggers less useful to downstream tasks such as translation and text-to-speech synthesis. This paper creates a new dataset of over 30,000 naturally-occurring non-trivial examples of noun-verb ambiguity. Taggers within 1% of each other when measured on the WSJ have accuracies ranging from 57% to 75% accuracy on this challenge set. Enhancing the strongest existing tagger with contextual word embeddings and targeted training data improves its accuracy to 89%, a 14% absolute (52% relative) improvement. Downstream, using just this enhanced tagger yields a 28% reduction in error over the prior best learned model for homograph disambiguation for textto-speech synthesis.</abstract>
<identifier type="citekey">elkahky-etal-2018-challenge</identifier>
<identifier type="doi">10.18653/v1/D18-1277</identifier>
<location>
<url>https://aclanthology.org/D18-1277</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>2562</start>
<end>2572</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Challenge Set and Methods for Noun-Verb Ambiguity
%A Elkahky, Ali
%A Webster, Kellie
%A Andor, Daniel
%A Pitler, Emily
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F elkahky-etal-2018-challenge
%X English part-of-speech taggers regularly make egregious errors related to noun-verb ambiguity, despite having achieved 97%+ accuracy on the WSJ Penn Treebank since 2002. These mistakes have been difficult to quantify and make taggers less useful to downstream tasks such as translation and text-to-speech synthesis. This paper creates a new dataset of over 30,000 naturally-occurring non-trivial examples of noun-verb ambiguity. Taggers within 1% of each other when measured on the WSJ have accuracies ranging from 57% to 75% accuracy on this challenge set. Enhancing the strongest existing tagger with contextual word embeddings and targeted training data improves its accuracy to 89%, a 14% absolute (52% relative) improvement. Downstream, using just this enhanced tagger yields a 28% reduction in error over the prior best learned model for homograph disambiguation for textto-speech synthesis.
%R 10.18653/v1/D18-1277
%U https://aclanthology.org/D18-1277
%U https://doi.org/10.18653/v1/D18-1277
%P 2562-2572
Markdown (Informal)
[A Challenge Set and Methods for Noun-Verb Ambiguity](https://aclanthology.org/D18-1277) (Elkahky et al., EMNLP 2018)
ACL
- Ali Elkahky, Kellie Webster, Daniel Andor, and Emily Pitler. 2018. A Challenge Set and Methods for Noun-Verb Ambiguity. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2562–2572, Brussels, Belgium. Association for Computational Linguistics.