@inproceedings{raheja-etal-2024-medit,
title = "m{E}d{IT}: Multilingual Text Editing via Instruction Tuning",
author = "Raheja, Vipul and
Alikaniotis, Dimitris and
Kulkarni, Vivek and
Alhafni, Bashar and
Kumar, Dhruv",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.56/",
doi = "10.18653/v1/2024.naacl-long.56",
pages = "979--1001",
abstract = "We introduce mEdIT, a multi-lingual extension to CoEdIT {--} the recent state-of-the-art text editing models for writing assistance. mEdIT models are trained by fine-tuning multi-lingual large, pre-trained language models (LLMs) via instruction tuning. They are designed to take instructions from the user specifying the attributes of the desired text in the form of natural language instructions, such as {\textquotedblleft}Grammatik korrigieren{\textquotedblright} (German) or {\textquotedblleft}이 텍스 트를 단순화{\textquotedblright} (Korean). We build mEdIT by curating data from multiple publicly available human-annotated text editing datasets for three text editing tasks (Grammatical Error Correction (GEC), Text Simplification, and Paraphrasing) across diverse languages belonging to six different language families. We detail the design and training of mEdIT models and demonstrate their strong performance on many multi-lingual text editing benchmarks against other multilingual LLMs. We also find that mEdIT generalizes effectively to new languages over multilingual baselines. We publicly release our data, code, and trained models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raheja-etal-2024-medit">
<titleInfo>
<title>mEdIT: Multilingual Text Editing via Instruction Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vipul</namePart>
<namePart type="family">Raheja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitris</namePart>
<namePart type="family">Alikaniotis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce mEdIT, a multi-lingual extension to CoEdIT – the recent state-of-the-art text editing models for writing assistance. mEdIT models are trained by fine-tuning multi-lingual large, pre-trained language models (LLMs) via instruction tuning. They are designed to take instructions from the user specifying the attributes of the desired text in the form of natural language instructions, such as “Grammatik korrigieren” (German) or “이 텍스 트를 단순화” (Korean). We build mEdIT by curating data from multiple publicly available human-annotated text editing datasets for three text editing tasks (Grammatical Error Correction (GEC), Text Simplification, and Paraphrasing) across diverse languages belonging to six different language families. We detail the design and training of mEdIT models and demonstrate their strong performance on many multi-lingual text editing benchmarks against other multilingual LLMs. We also find that mEdIT generalizes effectively to new languages over multilingual baselines. We publicly release our data, code, and trained models.</abstract>
<identifier type="citekey">raheja-etal-2024-medit</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.56</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.56/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>979</start>
<end>1001</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mEdIT: Multilingual Text Editing via Instruction Tuning
%A Raheja, Vipul
%A Alikaniotis, Dimitris
%A Kulkarni, Vivek
%A Alhafni, Bashar
%A Kumar, Dhruv
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F raheja-etal-2024-medit
%X We introduce mEdIT, a multi-lingual extension to CoEdIT – the recent state-of-the-art text editing models for writing assistance. mEdIT models are trained by fine-tuning multi-lingual large, pre-trained language models (LLMs) via instruction tuning. They are designed to take instructions from the user specifying the attributes of the desired text in the form of natural language instructions, such as “Grammatik korrigieren” (German) or “이 텍스 트를 단순화” (Korean). We build mEdIT by curating data from multiple publicly available human-annotated text editing datasets for three text editing tasks (Grammatical Error Correction (GEC), Text Simplification, and Paraphrasing) across diverse languages belonging to six different language families. We detail the design and training of mEdIT models and demonstrate their strong performance on many multi-lingual text editing benchmarks against other multilingual LLMs. We also find that mEdIT generalizes effectively to new languages over multilingual baselines. We publicly release our data, code, and trained models.
%R 10.18653/v1/2024.naacl-long.56
%U https://aclanthology.org/2024.naacl-long.56/
%U https://doi.org/10.18653/v1/2024.naacl-long.56
%P 979-1001
Markdown (Informal)
[mEdIT: Multilingual Text Editing via Instruction Tuning](https://aclanthology.org/2024.naacl-long.56/) (Raheja et al., NAACL 2024)
ACL
- Vipul Raheja, Dimitris Alikaniotis, Vivek Kulkarni, Bashar Alhafni, and Dhruv Kumar. 2024. mEdIT: Multilingual Text Editing via Instruction Tuning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 979–1001, Mexico City, Mexico. Association for Computational Linguistics.