@inproceedings{du-etal-2022-non,
title = "Non-Parametric Domain Adaptation for End-to-End Speech Translation",
author = "Du, Yichao and
Wang, Weizhi and
Zhang, Zhirui and
Chen, Boxing and
Xu, Tong and
Xie, Jun and
Chen, Enhong",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.21/",
doi = "10.18653/v1/2022.emnlp-main.21",
pages = "306--320",
abstract = "The end-to-end speech translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency and fewer parameters. However, the effectiveness of neural-based approaches to this task is severely limited by the available training corpus, especially for domain adaptation where in-domain triplet data is scarce or nonexistent. In this paper, we propose a novel non-parametric method that leverages in-domain text translation corpus to achieve domain adaptation for E2E-ST systems. To this end, we first incorporate an additional encoder into the pre-trained E2E-ST model to realize text translation modeling, based on which the decoder`s output representations for text and speech translation tasks are unified by reducing the correspondent representation mismatch in available triplet training data. During domain adaptation, a k-nearest-neighbor (kNN) classifier is introduced to produce the final translation distribution using the external datastore built by the domain-specific text translation corpus, while the universal output representation is adopted to perform a similarity search. Experiments on the Europarl-ST benchmark demonstrate that when in-domain text translation data is involved only, our proposed approach significantly improves baseline by 12.82 BLEU on average in all translation directions, even outperforming the strong in-domain fine-tuning strategy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-etal-2022-non">
<titleInfo>
<title>Non-Parametric Domain Adaptation for End-to-End Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weizhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhirui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enhong</namePart>
<namePart type="family">Chen</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 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The end-to-end speech translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency and fewer parameters. However, the effectiveness of neural-based approaches to this task is severely limited by the available training corpus, especially for domain adaptation where in-domain triplet data is scarce or nonexistent. In this paper, we propose a novel non-parametric method that leverages in-domain text translation corpus to achieve domain adaptation for E2E-ST systems. To this end, we first incorporate an additional encoder into the pre-trained E2E-ST model to realize text translation modeling, based on which the decoder‘s output representations for text and speech translation tasks are unified by reducing the correspondent representation mismatch in available triplet training data. During domain adaptation, a k-nearest-neighbor (kNN) classifier is introduced to produce the final translation distribution using the external datastore built by the domain-specific text translation corpus, while the universal output representation is adopted to perform a similarity search. Experiments on the Europarl-ST benchmark demonstrate that when in-domain text translation data is involved only, our proposed approach significantly improves baseline by 12.82 BLEU on average in all translation directions, even outperforming the strong in-domain fine-tuning strategy.</abstract>
<identifier type="citekey">du-etal-2022-non</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.21</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.21/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>306</start>
<end>320</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-Parametric Domain Adaptation for End-to-End Speech Translation
%A Du, Yichao
%A Wang, Weizhi
%A Zhang, Zhirui
%A Chen, Boxing
%A Xu, Tong
%A Xie, Jun
%A Chen, Enhong
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F du-etal-2022-non
%X The end-to-end speech translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency and fewer parameters. However, the effectiveness of neural-based approaches to this task is severely limited by the available training corpus, especially for domain adaptation where in-domain triplet data is scarce or nonexistent. In this paper, we propose a novel non-parametric method that leverages in-domain text translation corpus to achieve domain adaptation for E2E-ST systems. To this end, we first incorporate an additional encoder into the pre-trained E2E-ST model to realize text translation modeling, based on which the decoder‘s output representations for text and speech translation tasks are unified by reducing the correspondent representation mismatch in available triplet training data. During domain adaptation, a k-nearest-neighbor (kNN) classifier is introduced to produce the final translation distribution using the external datastore built by the domain-specific text translation corpus, while the universal output representation is adopted to perform a similarity search. Experiments on the Europarl-ST benchmark demonstrate that when in-domain text translation data is involved only, our proposed approach significantly improves baseline by 12.82 BLEU on average in all translation directions, even outperforming the strong in-domain fine-tuning strategy.
%R 10.18653/v1/2022.emnlp-main.21
%U https://aclanthology.org/2022.emnlp-main.21/
%U https://doi.org/10.18653/v1/2022.emnlp-main.21
%P 306-320
Markdown (Informal)
[Non-Parametric Domain Adaptation for End-to-End Speech Translation](https://aclanthology.org/2022.emnlp-main.21/) (Du et al., EMNLP 2022)
ACL
- Yichao Du, Weizhi Wang, Zhirui Zhang, Boxing Chen, Tong Xu, Jun Xie, and Enhong Chen. 2022. Non-Parametric Domain Adaptation for End-to-End Speech Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 306–320, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.