@inproceedings{bapna-firat-2019-non,
title = "Non-Parametric Adaptation for Neural Machine Translation",
author = "Bapna, Ankur and
Firat, Orhan",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1191/",
doi = "10.18653/v1/N19-1191",
pages = "1921--1931",
abstract = "Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance on heterogeneous datasets and on sub-tasks like rare phrase translation. On the other hand, non-parametric approaches are immune to forgetting, perfectly complementing the generalization ability of NMT. However, attempts to combine non-parametric or retrieval based approaches with NMT have only been successful on narrow domains, possibly due to over-reliance on sentence level retrieval. We propose a novel n-gram level retrieval approach that relies on local phrase level similarities, allowing us to retrieve neighbors that are useful for translation even when overall sentence similarity is low. We complement this with an expressive neural network, allowing our model to extract information from the noisy retrieved context. We evaluate our Semi-parametric NMT approach on a heterogeneous dataset composed of WMT, IWSLT, JRC-Acquis and OpenSubtitles, and demonstrate gains on all 4 evaluation sets. The Semi-parametric nature of our approach also opens the door for non-parametric domain adaptation, demonstrating strong inference-time adaptation performance on new domains without the need for any parameter updates."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bapna-firat-2019-non">
<titleInfo>
<title>Non-Parametric Adaptation for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankur</namePart>
<namePart type="family">Bapna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orhan</namePart>
<namePart type="family">Firat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance on heterogeneous datasets and on sub-tasks like rare phrase translation. On the other hand, non-parametric approaches are immune to forgetting, perfectly complementing the generalization ability of NMT. However, attempts to combine non-parametric or retrieval based approaches with NMT have only been successful on narrow domains, possibly due to over-reliance on sentence level retrieval. We propose a novel n-gram level retrieval approach that relies on local phrase level similarities, allowing us to retrieve neighbors that are useful for translation even when overall sentence similarity is low. We complement this with an expressive neural network, allowing our model to extract information from the noisy retrieved context. We evaluate our Semi-parametric NMT approach on a heterogeneous dataset composed of WMT, IWSLT, JRC-Acquis and OpenSubtitles, and demonstrate gains on all 4 evaluation sets. The Semi-parametric nature of our approach also opens the door for non-parametric domain adaptation, demonstrating strong inference-time adaptation performance on new domains without the need for any parameter updates.</abstract>
<identifier type="citekey">bapna-firat-2019-non</identifier>
<identifier type="doi">10.18653/v1/N19-1191</identifier>
<location>
<url>https://aclanthology.org/N19-1191/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1921</start>
<end>1931</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-Parametric Adaptation for Neural Machine Translation
%A Bapna, Ankur
%A Firat, Orhan
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F bapna-firat-2019-non
%X Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance on heterogeneous datasets and on sub-tasks like rare phrase translation. On the other hand, non-parametric approaches are immune to forgetting, perfectly complementing the generalization ability of NMT. However, attempts to combine non-parametric or retrieval based approaches with NMT have only been successful on narrow domains, possibly due to over-reliance on sentence level retrieval. We propose a novel n-gram level retrieval approach that relies on local phrase level similarities, allowing us to retrieve neighbors that are useful for translation even when overall sentence similarity is low. We complement this with an expressive neural network, allowing our model to extract information from the noisy retrieved context. We evaluate our Semi-parametric NMT approach on a heterogeneous dataset composed of WMT, IWSLT, JRC-Acquis and OpenSubtitles, and demonstrate gains on all 4 evaluation sets. The Semi-parametric nature of our approach also opens the door for non-parametric domain adaptation, demonstrating strong inference-time adaptation performance on new domains without the need for any parameter updates.
%R 10.18653/v1/N19-1191
%U https://aclanthology.org/N19-1191/
%U https://doi.org/10.18653/v1/N19-1191
%P 1921-1931
Markdown (Informal)
[Non-Parametric Adaptation for Neural Machine Translation](https://aclanthology.org/N19-1191/) (Bapna & Firat, NAACL 2019)
ACL
- Ankur Bapna and Orhan Firat. 2019. Non-Parametric Adaptation for Neural Machine Translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1921–1931, Minneapolis, Minnesota. Association for Computational Linguistics.