<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehrparvar-pezzelle-2024-detecting">
    <titleInfo>
        <title>Detecting and Translating Language Ambiguity with Multilingual LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Behrang</namePart>
        <namePart type="family">Mehrparvar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sandro</namePart>
        <namePart type="family">Pezzelle</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jonne</namePart>
            <namePart type="family">Sälevä</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abraham</namePart>
            <namePart type="family">Owodunni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Most languages could be ambiguous, which means the same conveyed text or speech, results in different actions by different readers or listeners. In this project, we propose a method to detect the ambiguity of a sentence using translation by multilingual LLMs. In particular, we hypothesize that a good machine translator should preserve the ambiguity of sentences in all target languages. Therefore, we investigate whether ambiguity is encoded in the hidden representation of a translation model or, instead, if only a single meaning is encoded. In our experiments, we have been able to predict ambiguity of sentences with high accuracy using machine translation without direct use of semantics and only based on the reconstruction error of a function that maps the forward and backward translation hidden representations to each other. The potential applications of the proposed approach span i) detecting ambiguous sentences, ii) fine-tuning existing multilingual LLMs to preserve ambiguous information, and iii) developing AI systems that can generate ambiguity-free languages when needed.</abstract>
    <identifier type="citekey">mehrparvar-pezzelle-2024-detecting</identifier>
    <location>
        <url>https://aclanthology.org/2024.mrl-1.26</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>310</start>
            <end>323</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Detecting and Translating Language Ambiguity with Multilingual LLMs
%A Mehrparvar, Behrang
%A Pezzelle, Sandro
%Y Sälevä, Jonne
%Y Owodunni, Abraham
%S Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F mehrparvar-pezzelle-2024-detecting
%X Most languages could be ambiguous, which means the same conveyed text or speech, results in different actions by different readers or listeners. In this project, we propose a method to detect the ambiguity of a sentence using translation by multilingual LLMs. In particular, we hypothesize that a good machine translator should preserve the ambiguity of sentences in all target languages. Therefore, we investigate whether ambiguity is encoded in the hidden representation of a translation model or, instead, if only a single meaning is encoded. In our experiments, we have been able to predict ambiguity of sentences with high accuracy using machine translation without direct use of semantics and only based on the reconstruction error of a function that maps the forward and backward translation hidden representations to each other. The potential applications of the proposed approach span i) detecting ambiguous sentences, ii) fine-tuning existing multilingual LLMs to preserve ambiguous information, and iii) developing AI systems that can generate ambiguity-free languages when needed.
%U https://aclanthology.org/2024.mrl-1.26
%P 310-323

Markdown (Informal)

[Detecting and Translating Language Ambiguity with Multilingual LLMs](https://aclanthology.org/2024.mrl-1.26) (Mehrparvar & Pezzelle, MRL 2024)

• Detecting and Translating Language Ambiguity with Multilingual LLMs (Mehrparvar & Pezzelle, MRL 2024)

ACL

• Behrang Mehrparvar and Sandro Pezzelle. 2024. Detecting and Translating Language Ambiguity with Multilingual LLMs. In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), pages 310–323, Miami, Florida, USA. Association for Computational Linguistics.