@inproceedings{pal-heafield-2022-cheat,
title = "Cheat Codes to Quantify Missing Source Information in Neural Machine Translation",
author = "Pal, Proyag and
Heafield, Kenneth",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.177/",
doi = "10.18653/v1/2022.naacl-main.177",
pages = "2472--2477",
abstract = "This paper describes a method to quantify the amount of information $H(t|s)$ added by the target sentence $t$ that is not present in the source $s$ in a neural machine translation system. We do this by providing the model the target sentence in a highly compressed form (a {\textquotedblleft}cheat code{\textquotedblright}), and exploring the effect of the size of the cheat code. We find that the model is able to capture extra information from just a single float representation of the target and nearly reproduces the target with two 32-bit floats per target token."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pal-heafield-2022-cheat">
<titleInfo>
<title>Cheat Codes to Quantify Missing Source Information in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Proyag</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Heafield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a method to quantify the amount of information H(t|s) added by the target sentence t that is not present in the source s in a neural machine translation system. We do this by providing the model the target sentence in a highly compressed form (a “cheat code”), and exploring the effect of the size of the cheat code. We find that the model is able to capture extra information from just a single float representation of the target and nearly reproduces the target with two 32-bit floats per target token.</abstract>
<identifier type="citekey">pal-heafield-2022-cheat</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.177</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.177/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2472</start>
<end>2477</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cheat Codes to Quantify Missing Source Information in Neural Machine Translation
%A Pal, Proyag
%A Heafield, Kenneth
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F pal-heafield-2022-cheat
%X This paper describes a method to quantify the amount of information H(t|s) added by the target sentence t that is not present in the source s in a neural machine translation system. We do this by providing the model the target sentence in a highly compressed form (a “cheat code”), and exploring the effect of the size of the cheat code. We find that the model is able to capture extra information from just a single float representation of the target and nearly reproduces the target with two 32-bit floats per target token.
%R 10.18653/v1/2022.naacl-main.177
%U https://aclanthology.org/2022.naacl-main.177/
%U https://doi.org/10.18653/v1/2022.naacl-main.177
%P 2472-2477
Markdown (Informal)
[Cheat Codes to Quantify Missing Source Information in Neural Machine Translation](https://aclanthology.org/2022.naacl-main.177/) (Pal & Heafield, NAACL 2022)
ACL