<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rippeth-post-2022-additive">
    <titleInfo>
        <title>Additive Interventions Yield Robust Multi-Domain Machine Translation Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Elijah</namePart>
        <namePart type="family">Rippeth</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matt</namePart>
        <namePart type="family">Post</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Seventh Conference on Machine Translation (WMT)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Additive interventions are a recently-proposed mechanism for controlling target-side attributes in neural machine translation by modulating the encoder’s representation of a source sequence as opposed to manipulating the raw source sequence as seen in most previous tag-based approaches. In this work we examine the role of additive interventions in a large-scale multi-domain machine translation setting and compare its performance in various inference scenarios. We find that while the performance difference is small between intervention-based systems and tag-based systems when the domain label matches the test domain, intervention-based systems are robust to label error, making them an attractive choice under label uncertainty. Further, we find that the superiority of single-domain fine-tuning comes under question when training data is scaled, contradicting previous findings.</abstract>
    <identifier type="citekey">rippeth-post-2022-additive</identifier>
    <location>
        <url>https://aclanthology.org/2022.wmt-1.14</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>220</start>
            <end>232</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Additive Interventions Yield Robust Multi-Domain Machine Translation Models
%A Rippeth, Elijah
%A Post, Matt
%S Proceedings of the Seventh Conference on Machine Translation (WMT)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F rippeth-post-2022-additive
%X Additive interventions are a recently-proposed mechanism for controlling target-side attributes in neural machine translation by modulating the encoder’s representation of a source sequence as opposed to manipulating the raw source sequence as seen in most previous tag-based approaches. In this work we examine the role of additive interventions in a large-scale multi-domain machine translation setting and compare its performance in various inference scenarios. We find that while the performance difference is small between intervention-based systems and tag-based systems when the domain label matches the test domain, intervention-based systems are robust to label error, making them an attractive choice under label uncertainty. Further, we find that the superiority of single-domain fine-tuning comes under question when training data is scaled, contradicting previous findings.
%U https://aclanthology.org/2022.wmt-1.14
%P 220-232

Markdown (Informal)

[Additive Interventions Yield Robust Multi-Domain Machine Translation Models](https://aclanthology.org/2022.wmt-1.14) (Rippeth & Post, WMT 2022)

• Additive Interventions Yield Robust Multi-Domain Machine Translation Models (Rippeth & Post, WMT 2022)

ACL

• Elijah Rippeth and Matt Post. 2022. Additive Interventions Yield Robust Multi-Domain Machine Translation Models. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 220–232, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.