@inproceedings{vamvas-sennrich-2021-limits,
title = "On the Limits of Minimal Pairs in Contrastive Evaluation",
author = "Vamvas, Jannis and
Sennrich, Rico",
editor = "Bastings, Jasmijn and
Belinkov, Yonatan and
Dupoux, Emmanuel and
Giulianelli, Mario and
Hupkes, Dieuwke and
Pinter, Yuval and
Sajjad, Hassan",
booktitle = "Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.blackboxnlp-1.5/",
doi = "10.18653/v1/2021.blackboxnlp-1.5",
pages = "58--68",
abstract = "Minimal sentence pairs are frequently used to analyze the behavior of language models. It is often assumed that model behavior on contrastive pairs is predictive of model behavior at large. We argue that two conditions are necessary for this assumption to hold: First, a tested hypothesis should be well-motivated, since experiments show that contrastive evaluation can lead to false positives. Secondly, test data should be chosen such as to minimize distributional discrepancy between evaluation time and deployment time. For a good approximation of deployment-time decoding, we recommend that minimal pairs are created based on machine-generated text, as opposed to human-written references. We present a contrastive evaluation suite for English{--}German MT that implements this recommendation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vamvas-sennrich-2021-limits">
<titleInfo>
<title>On the Limits of Minimal Pairs in Contrastive Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jannis</namePart>
<namePart type="family">Vamvas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</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 Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasmijn</namePart>
<namePart type="family">Bastings</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Dupoux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Giulianelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Minimal sentence pairs are frequently used to analyze the behavior of language models. It is often assumed that model behavior on contrastive pairs is predictive of model behavior at large. We argue that two conditions are necessary for this assumption to hold: First, a tested hypothesis should be well-motivated, since experiments show that contrastive evaluation can lead to false positives. Secondly, test data should be chosen such as to minimize distributional discrepancy between evaluation time and deployment time. For a good approximation of deployment-time decoding, we recommend that minimal pairs are created based on machine-generated text, as opposed to human-written references. We present a contrastive evaluation suite for English–German MT that implements this recommendation.</abstract>
<identifier type="citekey">vamvas-sennrich-2021-limits</identifier>
<identifier type="doi">10.18653/v1/2021.blackboxnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.blackboxnlp-1.5/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>58</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Limits of Minimal Pairs in Contrastive Evaluation
%A Vamvas, Jannis
%A Sennrich, Rico
%Y Bastings, Jasmijn
%Y Belinkov, Yonatan
%Y Dupoux, Emmanuel
%Y Giulianelli, Mario
%Y Hupkes, Dieuwke
%Y Pinter, Yuval
%Y Sajjad, Hassan
%S Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F vamvas-sennrich-2021-limits
%X Minimal sentence pairs are frequently used to analyze the behavior of language models. It is often assumed that model behavior on contrastive pairs is predictive of model behavior at large. We argue that two conditions are necessary for this assumption to hold: First, a tested hypothesis should be well-motivated, since experiments show that contrastive evaluation can lead to false positives. Secondly, test data should be chosen such as to minimize distributional discrepancy between evaluation time and deployment time. For a good approximation of deployment-time decoding, we recommend that minimal pairs are created based on machine-generated text, as opposed to human-written references. We present a contrastive evaluation suite for English–German MT that implements this recommendation.
%R 10.18653/v1/2021.blackboxnlp-1.5
%U https://aclanthology.org/2021.blackboxnlp-1.5/
%U https://doi.org/10.18653/v1/2021.blackboxnlp-1.5
%P 58-68
Markdown (Informal)
[On the Limits of Minimal Pairs in Contrastive Evaluation](https://aclanthology.org/2021.blackboxnlp-1.5/) (Vamvas & Sennrich, BlackboxNLP 2021)
ACL
- Jannis Vamvas and Rico Sennrich. 2021. On the Limits of Minimal Pairs in Contrastive Evaluation. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 58–68, Punta Cana, Dominican Republic. Association for Computational Linguistics.