@inproceedings{kang-etal-2019-pomo,
title = "{P}o{M}o: Generating Entity-Specific Post-Modifiers in Context",
author = "Kang, Jun Seok and
Logan, Robert and
Chu, Zewei and
Chen, Yang and
Dua, Dheeru and
Gimpel, Kevin and
Singh, Sameer and
Balasubramanian, Niranjan",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1089",
doi = "10.18653/v1/N19-1089",
pages = "826--838",
abstract = "We introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity. For example, for the sentence, {``}Barack Obama, {\_}{\_}{\_}{\_}{\_}{\_}{\_}, supported the {\#}MeToo movement.{''}, the phrase {``}a father of two girls{''} is a contextually relevant post-modifier. To this end, we build PoMo, a post-modifier dataset created automatically from news articles reflecting a journalistic need for incorporating entity information that is relevant to a particular news event. PoMo consists of more than 231K sentences with post-modifiers and associated facts extracted from Wikidata for around 57K unique entities. We use crowdsourcing to show that modeling contextual relevance is necessary for accurate post-modifier generation. We adapt a number of existing generation approaches as baselines for this dataset. Our results show there is large room for improvement in terms of both identifying relevant facts to include (knowing which claims are relevant gives a {\textgreater}20{\%} improvement in BLEU score), and generating appropriate post-modifier text for the context (providing relevant claims is not sufficient for accurate generation). We conduct an error analysis that suggests promising directions for future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2019-pomo">
<titleInfo>
<title>PoMo: Generating Entity-Specific Post-Modifiers in Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="given">Seok</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Logan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zewei</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dheeru</namePart>
<namePart type="family">Dua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Gimpel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niranjan</namePart>
<namePart type="family">Balasubramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity. For example, for the sentence, “Barack Obama, _______, supported the #MeToo movement.”, the phrase “a father of two girls” is a contextually relevant post-modifier. To this end, we build PoMo, a post-modifier dataset created automatically from news articles reflecting a journalistic need for incorporating entity information that is relevant to a particular news event. PoMo consists of more than 231K sentences with post-modifiers and associated facts extracted from Wikidata for around 57K unique entities. We use crowdsourcing to show that modeling contextual relevance is necessary for accurate post-modifier generation. We adapt a number of existing generation approaches as baselines for this dataset. Our results show there is large room for improvement in terms of both identifying relevant facts to include (knowing which claims are relevant gives a \textgreater20% improvement in BLEU score), and generating appropriate post-modifier text for the context (providing relevant claims is not sufficient for accurate generation). We conduct an error analysis that suggests promising directions for future research.</abstract>
<identifier type="citekey">kang-etal-2019-pomo</identifier>
<identifier type="doi">10.18653/v1/N19-1089</identifier>
<location>
<url>https://aclanthology.org/N19-1089</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>826</start>
<end>838</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PoMo: Generating Entity-Specific Post-Modifiers in Context
%A Kang, Jun Seok
%A Logan, Robert
%A Chu, Zewei
%A Chen, Yang
%A Dua, Dheeru
%A Gimpel, Kevin
%A Singh, Sameer
%A Balasubramanian, Niranjan
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F kang-etal-2019-pomo
%X We introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-modifier phrase that provides contextually relevant information about the entity. For example, for the sentence, “Barack Obama, _______, supported the #MeToo movement.”, the phrase “a father of two girls” is a contextually relevant post-modifier. To this end, we build PoMo, a post-modifier dataset created automatically from news articles reflecting a journalistic need for incorporating entity information that is relevant to a particular news event. PoMo consists of more than 231K sentences with post-modifiers and associated facts extracted from Wikidata for around 57K unique entities. We use crowdsourcing to show that modeling contextual relevance is necessary for accurate post-modifier generation. We adapt a number of existing generation approaches as baselines for this dataset. Our results show there is large room for improvement in terms of both identifying relevant facts to include (knowing which claims are relevant gives a \textgreater20% improvement in BLEU score), and generating appropriate post-modifier text for the context (providing relevant claims is not sufficient for accurate generation). We conduct an error analysis that suggests promising directions for future research.
%R 10.18653/v1/N19-1089
%U https://aclanthology.org/N19-1089
%U https://doi.org/10.18653/v1/N19-1089
%P 826-838
Markdown (Informal)
[PoMo: Generating Entity-Specific Post-Modifiers in Context](https://aclanthology.org/N19-1089) (Kang et al., NAACL 2019)
ACL
- Jun Seok Kang, Robert Logan, Zewei Chu, Yang Chen, Dheeru Dua, Kevin Gimpel, Sameer Singh, and Niranjan Balasubramanian. 2019. PoMo: Generating Entity-Specific Post-Modifiers in Context. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 826–838, Minneapolis, Minnesota. Association for Computational Linguistics.