@inproceedings{kim-etal-2019-segmentation,
title = "Segmentation-free compositional $n$-gram embedding",
author = "Kim, Geewook and
Fukui, Kazuki and
Shimodaira, Hidetoshi",
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/N19-1324",
doi = "10.18653/v1/N19-1324",
pages = "3207--3215",
abstract = "We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very effective for noisy corpora written in unsegmented languages such as Chinese and Japanese. The main idea of our method is to ignore word boundaries completely (i.e., segmentation-free), and construct representations for all character $n$-grams in a raw corpus with embeddings of compositional sub-$n$-grams. Although the idea is simple, our experiments on various benchmarks and real-world datasets show the efficacy of our proposal.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2019-segmentation">
<titleInfo>
<title>Segmentation-free compositional n-gram embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geewook</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuki</namePart>
<namePart type="family">Fukui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetoshi</namePart>
<namePart type="family">Shimodaira</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 propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very effective for noisy corpora written in unsegmented languages such as Chinese and Japanese. The main idea of our method is to ignore word boundaries completely (i.e., segmentation-free), and construct representations for all character n-grams in a raw corpus with embeddings of compositional sub-n-grams. Although the idea is simple, our experiments on various benchmarks and real-world datasets show the efficacy of our proposal.</abstract>
<identifier type="citekey">kim-etal-2019-segmentation</identifier>
<identifier type="doi">10.18653/v1/N19-1324</identifier>
<location>
<url>https://aclanthology.org/N19-1324</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>3207</start>
<end>3215</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Segmentation-free compositional n-gram embedding
%A Kim, Geewook
%A Fukui, Kazuki
%A Shimodaira, Hidetoshi
%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 kim-etal-2019-segmentation
%X We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very effective for noisy corpora written in unsegmented languages such as Chinese and Japanese. The main idea of our method is to ignore word boundaries completely (i.e., segmentation-free), and construct representations for all character n-grams in a raw corpus with embeddings of compositional sub-n-grams. Although the idea is simple, our experiments on various benchmarks and real-world datasets show the efficacy of our proposal.
%R 10.18653/v1/N19-1324
%U https://aclanthology.org/N19-1324
%U https://doi.org/10.18653/v1/N19-1324
%P 3207-3215
Markdown (Informal)
[Segmentation-free compositional n-gram embedding](https://aclanthology.org/N19-1324) (Kim et al., NAACL 2019)
ACL
- Geewook Kim, Kazuki Fukui, and Hidetoshi Shimodaira. 2019. Segmentation-free compositional n-gram embedding. 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 3207–3215, Minneapolis, Minnesota. Association for Computational Linguistics.