@inproceedings{fung-wu-1994-statistical,
title = "Statistical Augmentation of a {C}hinese Machine-Readable Dictionary",
author = "Fung, Pascale and
Wu, Dekai",
booktitle = "Second Workshop on Very Large Corpora",
year = "1994",
url = "https://aclanthology.org/1994.vlc-1.6",
pages = "69--86",
abstract = "We describe a method of using statistically-collected Chinese character groups from a corpus to augment a Chinese dictionary. The method is particularly useful for extracting domain-specific and regional words not readily available in machine-readable dictionaries. Output was evaluated both using human evaluators and against a previously available dictionary. We also evaluated performance improvement in automatic Chinese tokenization. Results show that our method outputs legitimate words, acronymic constructions, idioms, names and titles, as well as technical compounds, many of which were lacking from the original dictionary.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fung-wu-1994-statistical">
<titleInfo>
<title>Statistical Augmentation of a Chinese Machine-Readable Dictionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dekai</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>1994</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Second Workshop on Very Large Corpora</title>
</titleInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe a method of using statistically-collected Chinese character groups from a corpus to augment a Chinese dictionary. The method is particularly useful for extracting domain-specific and regional words not readily available in machine-readable dictionaries. Output was evaluated both using human evaluators and against a previously available dictionary. We also evaluated performance improvement in automatic Chinese tokenization. Results show that our method outputs legitimate words, acronymic constructions, idioms, names and titles, as well as technical compounds, many of which were lacking from the original dictionary.</abstract>
<identifier type="citekey">fung-wu-1994-statistical</identifier>
<location>
<url>https://aclanthology.org/1994.vlc-1.6</url>
</location>
<part>
<date>1994</date>
<extent unit="page">
<start>69</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statistical Augmentation of a Chinese Machine-Readable Dictionary
%A Fung, Pascale
%A Wu, Dekai
%S Second Workshop on Very Large Corpora
%D 1994
%F fung-wu-1994-statistical
%X We describe a method of using statistically-collected Chinese character groups from a corpus to augment a Chinese dictionary. The method is particularly useful for extracting domain-specific and regional words not readily available in machine-readable dictionaries. Output was evaluated both using human evaluators and against a previously available dictionary. We also evaluated performance improvement in automatic Chinese tokenization. Results show that our method outputs legitimate words, acronymic constructions, idioms, names and titles, as well as technical compounds, many of which were lacking from the original dictionary.
%U https://aclanthology.org/1994.vlc-1.6
%P 69-86
Markdown (Informal)
[Statistical Augmentation of a Chinese Machine-Readable Dictionary](https://aclanthology.org/1994.vlc-1.6) (Fung & Wu, VLC 1994)
ACL