@inproceedings{lee-etal-2024-length,
title = "Length-aware Byte Pair Encoding for Mitigating Over-segmentation in {K}orean Machine Translation",
author = "Lee, Jungseob and
Moon, Hyeonseok and
Lee, Seungjun and
Park, Chanjun and
Eo, Sugyeong and
Ko, Hyunwoong and
Seo, Jaehyung and
Lee, Seungyoon and
Lim, Heuiseok",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.135",
doi = "10.18653/v1/2024.findings-acl.135",
pages = "2287--2303",
abstract = "Byte Pair Encoding is an effective approach in machine translation across several languages. However, our analysis indicates that BPE is prone to over-segmentation in the morphologically rich language, Korean, which can erode word semantics and lead to semantic confusion during training. This semantic confusion, stemming from over-segmentation, ultimately contributes to a degradation of overall translation quality. To address this issue, we introduce Length-aware Subword Vocabulary Construction (LeVoC), a novel approach strategically incorporating longer words into the vocabulary. By utilizing an external monolingual Korean corpus, LeVoC extracts and integrates long words, effectively preserving morphological information and reducing semantic confusion. Our experiments demonstrate that LeVoC not only significantly outperforms BPE, but also can be applied to and surpass current state-of-the-art morpheme-aware subword tokenization methods. We provide evidence that the difficulty in translating sentences with long words in Korean is associated with morphological compositionality, and LeVoC{'}s ability to reduce semantic confusion during training leads to improved translation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-length">
<titleInfo>
<title>Length-aware Byte Pair Encoding for Mitigating Over-segmentation in Korean Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jungseob</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeonseok</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungjun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanjun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sugyeong</namePart>
<namePart type="family">Eo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunwoong</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehyung</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungyoon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heuiseok</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Byte Pair Encoding is an effective approach in machine translation across several languages. However, our analysis indicates that BPE is prone to over-segmentation in the morphologically rich language, Korean, which can erode word semantics and lead to semantic confusion during training. This semantic confusion, stemming from over-segmentation, ultimately contributes to a degradation of overall translation quality. To address this issue, we introduce Length-aware Subword Vocabulary Construction (LeVoC), a novel approach strategically incorporating longer words into the vocabulary. By utilizing an external monolingual Korean corpus, LeVoC extracts and integrates long words, effectively preserving morphological information and reducing semantic confusion. Our experiments demonstrate that LeVoC not only significantly outperforms BPE, but also can be applied to and surpass current state-of-the-art morpheme-aware subword tokenization methods. We provide evidence that the difficulty in translating sentences with long words in Korean is associated with morphological compositionality, and LeVoC’s ability to reduce semantic confusion during training leads to improved translation quality.</abstract>
<identifier type="citekey">lee-etal-2024-length</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.135</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.135</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2287</start>
<end>2303</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Length-aware Byte Pair Encoding for Mitigating Over-segmentation in Korean Machine Translation
%A Lee, Jungseob
%A Moon, Hyeonseok
%A Lee, Seungjun
%A Park, Chanjun
%A Eo, Sugyeong
%A Ko, Hyunwoong
%A Seo, Jaehyung
%A Lee, Seungyoon
%A Lim, Heuiseok
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F lee-etal-2024-length
%X Byte Pair Encoding is an effective approach in machine translation across several languages. However, our analysis indicates that BPE is prone to over-segmentation in the morphologically rich language, Korean, which can erode word semantics and lead to semantic confusion during training. This semantic confusion, stemming from over-segmentation, ultimately contributes to a degradation of overall translation quality. To address this issue, we introduce Length-aware Subword Vocabulary Construction (LeVoC), a novel approach strategically incorporating longer words into the vocabulary. By utilizing an external monolingual Korean corpus, LeVoC extracts and integrates long words, effectively preserving morphological information and reducing semantic confusion. Our experiments demonstrate that LeVoC not only significantly outperforms BPE, but also can be applied to and surpass current state-of-the-art morpheme-aware subword tokenization methods. We provide evidence that the difficulty in translating sentences with long words in Korean is associated with morphological compositionality, and LeVoC’s ability to reduce semantic confusion during training leads to improved translation quality.
%R 10.18653/v1/2024.findings-acl.135
%U https://aclanthology.org/2024.findings-acl.135
%U https://doi.org/10.18653/v1/2024.findings-acl.135
%P 2287-2303
Markdown (Informal)
[Length-aware Byte Pair Encoding for Mitigating Over-segmentation in Korean Machine Translation](https://aclanthology.org/2024.findings-acl.135) (Lee et al., Findings 2024)
ACL
- Jungseob Lee, Hyeonseok Moon, Seungjun Lee, Chanjun Park, Sugyeong Eo, Hyunwoong Ko, Jaehyung Seo, Seungyoon Lee, and Heuiseok Lim. 2024. Length-aware Byte Pair Encoding for Mitigating Over-segmentation in Korean Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2287–2303, Bangkok, Thailand. Association for Computational Linguistics.