@inproceedings{parvez-etal-2018-building,
title = "Building Language Models for Text with Named Entities",
author = "Parvez, Md Rizwan and
Chakraborty, Saikat and
Ray, Baishakhi and
Chang, Kai-Wei",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1221",
doi = "10.18653/v1/P18-1221",
pages = "2373--2383",
abstract = "Text in many domains involves a significant amount of named entities. Predicting the entity names is often challenging for a language model as they appear less frequent on the training corpus. In this paper, we propose a novel and effective approach to building a language model which can learn the entity names by leveraging their entity type information. We also introduce two benchmark datasets based on recipes and Java programming codes, on which we evaluate the proposed model. Experimental results show that our model achieves 52.2{\%} better perplexity in recipe generation and 22.06{\%} on code generation than state-of-the-art language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parvez-etal-2018-building">
<titleInfo>
<title>Building Language Models for Text with Named Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rizwan</namePart>
<namePart type="family">Parvez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saikat</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baishakhi</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text in many domains involves a significant amount of named entities. Predicting the entity names is often challenging for a language model as they appear less frequent on the training corpus. In this paper, we propose a novel and effective approach to building a language model which can learn the entity names by leveraging their entity type information. We also introduce two benchmark datasets based on recipes and Java programming codes, on which we evaluate the proposed model. Experimental results show that our model achieves 52.2% better perplexity in recipe generation and 22.06% on code generation than state-of-the-art language models.</abstract>
<identifier type="citekey">parvez-etal-2018-building</identifier>
<identifier type="doi">10.18653/v1/P18-1221</identifier>
<location>
<url>https://aclanthology.org/P18-1221</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>2373</start>
<end>2383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building Language Models for Text with Named Entities
%A Parvez, Md Rizwan
%A Chakraborty, Saikat
%A Ray, Baishakhi
%A Chang, Kai-Wei
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F parvez-etal-2018-building
%X Text in many domains involves a significant amount of named entities. Predicting the entity names is often challenging for a language model as they appear less frequent on the training corpus. In this paper, we propose a novel and effective approach to building a language model which can learn the entity names by leveraging their entity type information. We also introduce two benchmark datasets based on recipes and Java programming codes, on which we evaluate the proposed model. Experimental results show that our model achieves 52.2% better perplexity in recipe generation and 22.06% on code generation than state-of-the-art language models.
%R 10.18653/v1/P18-1221
%U https://aclanthology.org/P18-1221
%U https://doi.org/10.18653/v1/P18-1221
%P 2373-2383
Markdown (Informal)
[Building Language Models for Text with Named Entities](https://aclanthology.org/P18-1221) (Parvez et al., ACL 2018)
ACL
- Md Rizwan Parvez, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2018. Building Language Models for Text with Named Entities. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2373–2383, Melbourne, Australia. Association for Computational Linguistics.