@inproceedings{shang-etal-2023-inarig,
title = "{IN}ar{IG}: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion",
author = "Shang, Hengchao and
Li, Zongyao and
Wei, Daimeng and
Guo, Jiaxin and
Wang, Minghan and
Chen, Xiaoyu and
Lei, Lizhi and
Yang, Hao",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.948",
doi = "10.18653/v1/2023.findings-emnlp.948",
pages = "14217--14228",
abstract = "Computer-aided translation (CAT) aims to enhance human translation efficiency and is still important in scenarios where machine translation cannot meet quality requirements. One fundamental task within this field is Word-Level Auto Completion (WLAC). WLAC predicts a target word given a source sentence, translation context, and a human typed character sequence. Previous works either employ word classification models to exploit contextual information from both sides of the target word or directly disregarded the dependencies from the right-side context. Furthermore, the key information, i.e. human typed sequences, is only used as prefix constraints in the decoding module. In this paper, we propose the INarIG (Iterative Non-autoregressive Instruct Generation) model, which constructs the human typed sequence into Instruction Unit and employs iterative decoding with subwords to fully utilize input information given in the task. Our model is more competent in dealing with low-frequency words (core scenario of this task), and achieves state-of-the-art results on the WMT22 and benchmark datasets, with a maximum increase of over 10{\%} prediction accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shang-etal-2023-inarig">
<titleInfo>
<title>INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhi</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</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>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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>Computer-aided translation (CAT) aims to enhance human translation efficiency and is still important in scenarios where machine translation cannot meet quality requirements. One fundamental task within this field is Word-Level Auto Completion (WLAC). WLAC predicts a target word given a source sentence, translation context, and a human typed character sequence. Previous works either employ word classification models to exploit contextual information from both sides of the target word or directly disregarded the dependencies from the right-side context. Furthermore, the key information, i.e. human typed sequences, is only used as prefix constraints in the decoding module. In this paper, we propose the INarIG (Iterative Non-autoregressive Instruct Generation) model, which constructs the human typed sequence into Instruction Unit and employs iterative decoding with subwords to fully utilize input information given in the task. Our model is more competent in dealing with low-frequency words (core scenario of this task), and achieves state-of-the-art results on the WMT22 and benchmark datasets, with a maximum increase of over 10% prediction accuracy.</abstract>
<identifier type="citekey">shang-etal-2023-inarig</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.948</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.948</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14217</start>
<end>14228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion
%A Shang, Hengchao
%A Li, Zongyao
%A Wei, Daimeng
%A Guo, Jiaxin
%A Wang, Minghan
%A Chen, Xiaoyu
%A Lei, Lizhi
%A Yang, Hao
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F shang-etal-2023-inarig
%X Computer-aided translation (CAT) aims to enhance human translation efficiency and is still important in scenarios where machine translation cannot meet quality requirements. One fundamental task within this field is Word-Level Auto Completion (WLAC). WLAC predicts a target word given a source sentence, translation context, and a human typed character sequence. Previous works either employ word classification models to exploit contextual information from both sides of the target word or directly disregarded the dependencies from the right-side context. Furthermore, the key information, i.e. human typed sequences, is only used as prefix constraints in the decoding module. In this paper, we propose the INarIG (Iterative Non-autoregressive Instruct Generation) model, which constructs the human typed sequence into Instruction Unit and employs iterative decoding with subwords to fully utilize input information given in the task. Our model is more competent in dealing with low-frequency words (core scenario of this task), and achieves state-of-the-art results on the WMT22 and benchmark datasets, with a maximum increase of over 10% prediction accuracy.
%R 10.18653/v1/2023.findings-emnlp.948
%U https://aclanthology.org/2023.findings-emnlp.948
%U https://doi.org/10.18653/v1/2023.findings-emnlp.948
%P 14217-14228
Markdown (Informal)
[INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion](https://aclanthology.org/2023.findings-emnlp.948) (Shang et al., Findings 2023)
ACL