@inproceedings{shapiro-2016-splitting,
title = "Splitting compounds with ngrams",
author = "Shapiro, Naomi Tachikawa",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1061",
pages = "630--640",
abstract = "Compound words with unmarked word boundaries are problematic for many tasks in NLP and computational linguistics, including information extraction, machine translation, and syllabification. This paper introduces a simple, proof-of-concept language modeling approach to automatic compound segmentation, as applied to Finnish. This approach utilizes an off-the-shelf morphological analyzer to split training words into their constituent morphemes. A language model is subsequently trained on ngrams composed of morphemes, morpheme boundaries, and word boundaries. Linguistic constraints are then used to weed out phonotactically ill-formed segmentations, thereby allowing the language model to select the best grammatical segmentation. This approach achieves an accuracy of {\textasciitilde}97{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shapiro-2016-splitting">
<titleInfo>
<title>Splitting compounds with ngrams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="given">Tachikawa</namePart>
<namePart type="family">Shapiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Compound words with unmarked word boundaries are problematic for many tasks in NLP and computational linguistics, including information extraction, machine translation, and syllabification. This paper introduces a simple, proof-of-concept language modeling approach to automatic compound segmentation, as applied to Finnish. This approach utilizes an off-the-shelf morphological analyzer to split training words into their constituent morphemes. A language model is subsequently trained on ngrams composed of morphemes, morpheme boundaries, and word boundaries. Linguistic constraints are then used to weed out phonotactically ill-formed segmentations, thereby allowing the language model to select the best grammatical segmentation. This approach achieves an accuracy of ~97%.</abstract>
<identifier type="citekey">shapiro-2016-splitting</identifier>
<location>
<url>https://aclanthology.org/C16-1061</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>630</start>
<end>640</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Splitting compounds with ngrams
%A Shapiro, Naomi Tachikawa
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F shapiro-2016-splitting
%X Compound words with unmarked word boundaries are problematic for many tasks in NLP and computational linguistics, including information extraction, machine translation, and syllabification. This paper introduces a simple, proof-of-concept language modeling approach to automatic compound segmentation, as applied to Finnish. This approach utilizes an off-the-shelf morphological analyzer to split training words into their constituent morphemes. A language model is subsequently trained on ngrams composed of morphemes, morpheme boundaries, and word boundaries. Linguistic constraints are then used to weed out phonotactically ill-formed segmentations, thereby allowing the language model to select the best grammatical segmentation. This approach achieves an accuracy of ~97%.
%U https://aclanthology.org/C16-1061
%P 630-640
Markdown (Informal)
[Splitting compounds with ngrams](https://aclanthology.org/C16-1061) (Shapiro, COLING 2016)
ACL
- Naomi Tachikawa Shapiro. 2016. Splitting compounds with ngrams. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 630–640, Osaka, Japan. The COLING 2016 Organizing Committee.