<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kambhatla-etal-2023-learning">
    <titleInfo>
        <title>Learning Nearest Neighbour Informed Latent Word Embeddings to Improve Zero-Shot Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nishant</namePart>
        <namePart type="family">Kambhatla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Logan</namePart>
        <namePart type="family">Born</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anoop</namePart>
        <namePart type="family">Sarkar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Elizabeth</namePart>
            <namePart type="family">Salesky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcello</namePart>
            <namePart type="family">Federico</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marine</namePart>
            <namePart type="family">Carpuat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multilingual neural translation models exploit cross-lingual transfer to perform zero-shot translation between unseen language pairs. Past efforts to improve cross-lingual transfer have focused on aligning contextual sentence-level representations. This paper introduces three novel contributions to allow exploiting nearest neighbours at the token level during training, including: (i) an efficient, gradient-friendly way to share representations between neighboring tokens; (ii) an attentional semantic layer which extracts latent features from shared embeddings; and (iii) an agreement loss to harmonize predictions across different sentence representations. Experiments on two multilingual datasets demonstrate consistent gains in zero shot translation over strong baselines.</abstract>
    <identifier type="citekey">kambhatla-etal-2023-learning</identifier>
    <identifier type="doi">10.18653/v1/2023.iwslt-1.27</identifier>
    <location>
        <url>https://aclanthology.org/2023.iwslt-1.27</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>291</start>
            <end>301</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Nearest Neighbour Informed Latent Word Embeddings to Improve Zero-Shot Machine Translation
%A Kambhatla, Nishant
%A Born, Logan
%A Sarkar, Anoop
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F kambhatla-etal-2023-learning
%X Multilingual neural translation models exploit cross-lingual transfer to perform zero-shot translation between unseen language pairs. Past efforts to improve cross-lingual transfer have focused on aligning contextual sentence-level representations. This paper introduces three novel contributions to allow exploiting nearest neighbours at the token level during training, including: (i) an efficient, gradient-friendly way to share representations between neighboring tokens; (ii) an attentional semantic layer which extracts latent features from shared embeddings; and (iii) an agreement loss to harmonize predictions across different sentence representations. Experiments on two multilingual datasets demonstrate consistent gains in zero shot translation over strong baselines.
%R 10.18653/v1/2023.iwslt-1.27
%U https://aclanthology.org/2023.iwslt-1.27
%U https://doi.org/10.18653/v1/2023.iwslt-1.27
%P 291-301

Markdown (Informal)

[Learning Nearest Neighbour Informed Latent Word Embeddings to Improve Zero-Shot Machine Translation](https://aclanthology.org/2023.iwslt-1.27) (Kambhatla et al., IWSLT 2023)

• Learning Nearest Neighbour Informed Latent Word Embeddings to Improve Zero-Shot Machine Translation (Kambhatla et al., IWSLT 2023)

ACL

• Nishant Kambhatla, Logan Born, and Anoop Sarkar. 2023. Learning Nearest Neighbour Informed Latent Word Embeddings to Improve Zero-Shot Machine Translation. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 291–301, Toronto, Canada (in-person and online). Association for Computational Linguistics.