@inproceedings{gaido-etal-2021-moby,
title = "Is {\textquotedblleft}moby dick{\textquotedblright} a Whale or a Bird? Named Entities and Terminology in Speech Translation",
author = "Gaido, Marco and
Rodr{\'i}guez, Susana and
Negri, Matteo and
Bentivogli, Luisa and
Turchi, Marco",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.128/",
doi = "10.18653/v1/2021.emnlp-main.128",
pages = "1707--1716",
abstract = "Automatic translation systems are known to struggle with rare words. Among these, named entities (NEs) and domain-specific terms are crucial, since errors in their translation can lead to severe meaning distortions. Despite their importance, previous speech translation (ST) studies have neglected them, also due to the dearth of publicly available resources tailored to their specific evaluation. To fill this gap, we i) present the first systematic analysis of the behavior of state-of-the-art ST systems in translating NEs and terminology, and ii) release NEuRoparl-ST, a novel benchmark built from European Parliament speeches annotated with NEs and terminology. Our experiments on the three language directions covered by our benchmark (en{\textrightarrow}es/fr/it) show that ST systems correctly translate 75{--}80{\%} of terms and 65{--}70{\%} of NEs, with very low performance (37{--}40{\%}) on person names."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaido-etal-2021-moby">
<titleInfo>
<title>Is “moby dick” a Whale or a Bird? Named Entities and Terminology in Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susana</namePart>
<namePart type="family">Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic translation systems are known to struggle with rare words. Among these, named entities (NEs) and domain-specific terms are crucial, since errors in their translation can lead to severe meaning distortions. Despite their importance, previous speech translation (ST) studies have neglected them, also due to the dearth of publicly available resources tailored to their specific evaluation. To fill this gap, we i) present the first systematic analysis of the behavior of state-of-the-art ST systems in translating NEs and terminology, and ii) release NEuRoparl-ST, a novel benchmark built from European Parliament speeches annotated with NEs and terminology. Our experiments on the three language directions covered by our benchmark (en→es/fr/it) show that ST systems correctly translate 75–80% of terms and 65–70% of NEs, with very low performance (37–40%) on person names.</abstract>
<identifier type="citekey">gaido-etal-2021-moby</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.128</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.128/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1707</start>
<end>1716</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is “moby dick” a Whale or a Bird? Named Entities and Terminology in Speech Translation
%A Gaido, Marco
%A Rodríguez, Susana
%A Negri, Matteo
%A Bentivogli, Luisa
%A Turchi, Marco
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F gaido-etal-2021-moby
%X Automatic translation systems are known to struggle with rare words. Among these, named entities (NEs) and domain-specific terms are crucial, since errors in their translation can lead to severe meaning distortions. Despite their importance, previous speech translation (ST) studies have neglected them, also due to the dearth of publicly available resources tailored to their specific evaluation. To fill this gap, we i) present the first systematic analysis of the behavior of state-of-the-art ST systems in translating NEs and terminology, and ii) release NEuRoparl-ST, a novel benchmark built from European Parliament speeches annotated with NEs and terminology. Our experiments on the three language directions covered by our benchmark (en→es/fr/it) show that ST systems correctly translate 75–80% of terms and 65–70% of NEs, with very low performance (37–40%) on person names.
%R 10.18653/v1/2021.emnlp-main.128
%U https://aclanthology.org/2021.emnlp-main.128/
%U https://doi.org/10.18653/v1/2021.emnlp-main.128
%P 1707-1716
Markdown (Informal)
[Is “moby dick” a Whale or a Bird? Named Entities and Terminology in Speech Translation](https://aclanthology.org/2021.emnlp-main.128/) (Gaido et al., EMNLP 2021)
ACL