@inproceedings{gekhman-etal-2020-kobe,
title = "{K}o{BE}: Knowledge-Based Machine Translation Evaluation",
author = "Gekhman, Zorik and
Aharoni, Roee and
Beryozkin, Genady and
Freitag, Markus and
Macherey, Wolfgang",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.287",
doi = "10.18653/v1/2020.findings-emnlp.287",
pages = "3200--3207",
abstract = "We propose a simple and effective method for machine translation evaluation which does not require reference translations. Our approach is based on (1) grounding the entity mentions found in each source sentence and candidate translation against a large-scale multilingual knowledge base, and (2) measuring the recall of the grounded entities found in the candidate vs. those found in the source. Our approach achieves the highest correlation with human judgements on 9 out of the 18 language pairs from the WMT19 benchmark for evaluation without references, which is the largest number of wins for a single evaluation method on this task. On 4 language pairs, we also achieve higher correlation with human judgements than BLEU. To foster further research, we release a dataset containing 1.8 million grounded entity mentions across 18 language pairs from the WMT19 metrics track data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gekhman-etal-2020-kobe">
<titleInfo>
<title>KoBE: Knowledge-Based Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zorik</namePart>
<namePart type="family">Gekhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roee</namePart>
<namePart type="family">Aharoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genady</namePart>
<namePart type="family">Beryozkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Macherey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a simple and effective method for machine translation evaluation which does not require reference translations. Our approach is based on (1) grounding the entity mentions found in each source sentence and candidate translation against a large-scale multilingual knowledge base, and (2) measuring the recall of the grounded entities found in the candidate vs. those found in the source. Our approach achieves the highest correlation with human judgements on 9 out of the 18 language pairs from the WMT19 benchmark for evaluation without references, which is the largest number of wins for a single evaluation method on this task. On 4 language pairs, we also achieve higher correlation with human judgements than BLEU. To foster further research, we release a dataset containing 1.8 million grounded entity mentions across 18 language pairs from the WMT19 metrics track data.</abstract>
<identifier type="citekey">gekhman-etal-2020-kobe</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.287</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.287</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3200</start>
<end>3207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KoBE: Knowledge-Based Machine Translation Evaluation
%A Gekhman, Zorik
%A Aharoni, Roee
%A Beryozkin, Genady
%A Freitag, Markus
%A Macherey, Wolfgang
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F gekhman-etal-2020-kobe
%X We propose a simple and effective method for machine translation evaluation which does not require reference translations. Our approach is based on (1) grounding the entity mentions found in each source sentence and candidate translation against a large-scale multilingual knowledge base, and (2) measuring the recall of the grounded entities found in the candidate vs. those found in the source. Our approach achieves the highest correlation with human judgements on 9 out of the 18 language pairs from the WMT19 benchmark for evaluation without references, which is the largest number of wins for a single evaluation method on this task. On 4 language pairs, we also achieve higher correlation with human judgements than BLEU. To foster further research, we release a dataset containing 1.8 million grounded entity mentions across 18 language pairs from the WMT19 metrics track data.
%R 10.18653/v1/2020.findings-emnlp.287
%U https://aclanthology.org/2020.findings-emnlp.287
%U https://doi.org/10.18653/v1/2020.findings-emnlp.287
%P 3200-3207
Markdown (Informal)
[KoBE: Knowledge-Based Machine Translation Evaluation](https://aclanthology.org/2020.findings-emnlp.287) (Gekhman et al., Findings 2020)
ACL
- Zorik Gekhman, Roee Aharoni, Genady Beryozkin, Markus Freitag, and Wolfgang Macherey. 2020. KoBE: Knowledge-Based Machine Translation Evaluation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3200–3207, Online. Association for Computational Linguistics.