@inproceedings{sarhangzadeh-watanabe-2024-alignment,
title = "Alignment-Based Decoding Policy for Low-Latency and Anticipation-Free Neural {J}apanese Input Method Editors",
author = "Sarhangzadeh, Armin and
Watanabe, Taro",
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.479/",
doi = "10.18653/v1/2024.findings-acl.479",
pages = "8043--8054",
abstract = "Japanese input method editors (IMEs) are essential tools for inputting Japanese text using a limited set of characters such as the kana syllabary. However, despite their importance, the potential of newer attention-based encoder-decoder neural networks, such as Transformer, has not yet been fully explored for IMEs due to their high computational cost and low-quality intermediate output in simultaneous settings, leading to high latencies. In this work, we propose a simple decoding policy to enable the use of attention-based encoder-decoder networks for simultaneous kana-kanji conversion in the context of Japanese IMEs inspired by simultaneous machine translation (SimulMT). We demonstrate that simply decoding by explicitly considering the word boundaries achieves a fairly strong quality-latency trade-off, as it can be seen as equivalent to performing decoding on aligned prefixes and thus achieving an incremental anticipation-free conversion. We further show how such a policy can be applied in practice to achieve high-quality conversions with minimal computational overhead. Our experiments show that our approach can achieve a noticeably better quality-latency trade-off compared to the baselines, while also being a more practical approach due to its ability to directly handle streaming input. Our code is available at https://anonymous.4open.science/r/transformer{\_}ime-D327."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarhangzadeh-watanabe-2024-alignment">
<titleInfo>
<title>Alignment-Based Decoding Policy for Low-Latency and Anticipation-Free Neural Japanese Input Method Editors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Armin</namePart>
<namePart type="family">Sarhangzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</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>Japanese input method editors (IMEs) are essential tools for inputting Japanese text using a limited set of characters such as the kana syllabary. However, despite their importance, the potential of newer attention-based encoder-decoder neural networks, such as Transformer, has not yet been fully explored for IMEs due to their high computational cost and low-quality intermediate output in simultaneous settings, leading to high latencies. In this work, we propose a simple decoding policy to enable the use of attention-based encoder-decoder networks for simultaneous kana-kanji conversion in the context of Japanese IMEs inspired by simultaneous machine translation (SimulMT). We demonstrate that simply decoding by explicitly considering the word boundaries achieves a fairly strong quality-latency trade-off, as it can be seen as equivalent to performing decoding on aligned prefixes and thus achieving an incremental anticipation-free conversion. We further show how such a policy can be applied in practice to achieve high-quality conversions with minimal computational overhead. Our experiments show that our approach can achieve a noticeably better quality-latency trade-off compared to the baselines, while also being a more practical approach due to its ability to directly handle streaming input. Our code is available at https://anonymous.4open.science/r/transformer_ime-D327.</abstract>
<identifier type="citekey">sarhangzadeh-watanabe-2024-alignment</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.479</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.479/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8043</start>
<end>8054</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alignment-Based Decoding Policy for Low-Latency and Anticipation-Free Neural Japanese Input Method Editors
%A Sarhangzadeh, Armin
%A Watanabe, Taro
%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 sarhangzadeh-watanabe-2024-alignment
%X Japanese input method editors (IMEs) are essential tools for inputting Japanese text using a limited set of characters such as the kana syllabary. However, despite their importance, the potential of newer attention-based encoder-decoder neural networks, such as Transformer, has not yet been fully explored for IMEs due to their high computational cost and low-quality intermediate output in simultaneous settings, leading to high latencies. In this work, we propose a simple decoding policy to enable the use of attention-based encoder-decoder networks for simultaneous kana-kanji conversion in the context of Japanese IMEs inspired by simultaneous machine translation (SimulMT). We demonstrate that simply decoding by explicitly considering the word boundaries achieves a fairly strong quality-latency trade-off, as it can be seen as equivalent to performing decoding on aligned prefixes and thus achieving an incremental anticipation-free conversion. We further show how such a policy can be applied in practice to achieve high-quality conversions with minimal computational overhead. Our experiments show that our approach can achieve a noticeably better quality-latency trade-off compared to the baselines, while also being a more practical approach due to its ability to directly handle streaming input. Our code is available at https://anonymous.4open.science/r/transformer_ime-D327.
%R 10.18653/v1/2024.findings-acl.479
%U https://aclanthology.org/2024.findings-acl.479/
%U https://doi.org/10.18653/v1/2024.findings-acl.479
%P 8043-8054
Markdown (Informal)
[Alignment-Based Decoding Policy for Low-Latency and Anticipation-Free Neural Japanese Input Method Editors](https://aclanthology.org/2024.findings-acl.479/) (Sarhangzadeh & Watanabe, Findings 2024)
- Alignment-Based Decoding Policy for Low-Latency and Anticipation-Free Neural Japanese Input Method Editors (Sarhangzadeh & Watanabe, Findings 2024)
ACL
- Armin Sarhangzadeh and Taro Watanabe. 2024. Alignment-Based Decoding Policy for Low-Latency and Anticipation-Free Neural Japanese Input Method Editors. In Findings of the Association for Computational Linguistics: ACL 2024, pages 8043–8054, Bangkok, Thailand. Association for Computational Linguistics.