@inproceedings{kaji-2023-lattice,
title = "Lattice Path Edit Distance: A {R}omanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from {J}apanese Search Query Logs",
author = "Kaji, Nobuhiro",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.24",
doi = "10.18653/v1/2023.emnlp-industry.24",
pages = "233--242",
abstract = "Edit distance has been successfully used to extract training data, i.e., misspelling-correction pairs, of spelling correction models from search query logs in languages including English. However, the success does not readily apply to Japanese, where misspellings are often dissimilar to correct spellings due to the romanization-based input methods. To address this problem, we introduce lattice path edit distance, which utilizes romanization lattices to efficiently consider all possible romanized forms of input strings. Empirical experiments using Japanese search query logs demonstrated that the lattice path edit distance outperformed baseline methods including the standard edit distance combined with an existing transliterator and morphological analyzer. A training data collection pipeline that uses the lattice path edit distance has been deployed in production at our search engine for over a year.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaji-2023-lattice">
<titleInfo>
<title>Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nobuhiro</namePart>
<namePart type="family">Kaji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Edit distance has been successfully used to extract training data, i.e., misspelling-correction pairs, of spelling correction models from search query logs in languages including English. However, the success does not readily apply to Japanese, where misspellings are often dissimilar to correct spellings due to the romanization-based input methods. To address this problem, we introduce lattice path edit distance, which utilizes romanization lattices to efficiently consider all possible romanized forms of input strings. Empirical experiments using Japanese search query logs demonstrated that the lattice path edit distance outperformed baseline methods including the standard edit distance combined with an existing transliterator and morphological analyzer. A training data collection pipeline that uses the lattice path edit distance has been deployed in production at our search engine for over a year.</abstract>
<identifier type="citekey">kaji-2023-lattice</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.24</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.24</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>233</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs
%A Kaji, Nobuhiro
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F kaji-2023-lattice
%X Edit distance has been successfully used to extract training data, i.e., misspelling-correction pairs, of spelling correction models from search query logs in languages including English. However, the success does not readily apply to Japanese, where misspellings are often dissimilar to correct spellings due to the romanization-based input methods. To address this problem, we introduce lattice path edit distance, which utilizes romanization lattices to efficiently consider all possible romanized forms of input strings. Empirical experiments using Japanese search query logs demonstrated that the lattice path edit distance outperformed baseline methods including the standard edit distance combined with an existing transliterator and morphological analyzer. A training data collection pipeline that uses the lattice path edit distance has been deployed in production at our search engine for over a year.
%R 10.18653/v1/2023.emnlp-industry.24
%U https://aclanthology.org/2023.emnlp-industry.24
%U https://doi.org/10.18653/v1/2023.emnlp-industry.24
%P 233-242
Markdown (Informal)
[Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs](https://aclanthology.org/2023.emnlp-industry.24) (Kaji, EMNLP 2023)
ACL