@inproceedings{cengiz-yuret-2020-joint,
title = "Joint Training with Semantic Role Labeling for Better Generalization in Natural Language Inference",
author = "Cengiz, Cemil and
Yuret, Deniz",
editor = "Gella, Spandana and
Welbl, Johannes and
Rei, Marek and
Petroni, Fabio and
Lewis, Patrick and
Strubell, Emma and
Seo, Minjoon and
Hajishirzi, Hannaneh",
booktitle = "Proceedings of the 5th Workshop on Representation Learning for NLP",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.repl4nlp-1.11",
doi = "10.18653/v1/2020.repl4nlp-1.11",
pages = "78--88",
abstract = "End-to-end models trained on natural language inference (NLI) datasets show low generalization on out-of-distribution evaluation sets. The models tend to learn shallow heuristics due to dataset biases. The performance decreases dramatically on diagnostic sets measuring compositionality or robustness against simple heuristics. Existing solutions for this problem employ dataset augmentation which has the drawbacks of being applicable to only a limited set of adversaries and at worst hurting the model performance on other adversaries not included in the augmentation set. Instead, our proposed solution is to improve sentence understanding (hence out-of-distribution generalization) with joint learning of explicit semantics. We show that a BERT based model trained jointly on English semantic role labeling (SRL) and NLI achieves significantly higher performance on external evaluation sets measuring generalization performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cengiz-yuret-2020-joint">
<titleInfo>
<title>Joint Training with Semantic Role Labeling for Better Generalization in Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cemil</namePart>
<namePart type="family">Cengiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deniz</namePart>
<namePart type="family">Yuret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Welbl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Petroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Strubell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</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>End-to-end models trained on natural language inference (NLI) datasets show low generalization on out-of-distribution evaluation sets. The models tend to learn shallow heuristics due to dataset biases. The performance decreases dramatically on diagnostic sets measuring compositionality or robustness against simple heuristics. Existing solutions for this problem employ dataset augmentation which has the drawbacks of being applicable to only a limited set of adversaries and at worst hurting the model performance on other adversaries not included in the augmentation set. Instead, our proposed solution is to improve sentence understanding (hence out-of-distribution generalization) with joint learning of explicit semantics. We show that a BERT based model trained jointly on English semantic role labeling (SRL) and NLI achieves significantly higher performance on external evaluation sets measuring generalization performance.</abstract>
<identifier type="citekey">cengiz-yuret-2020-joint</identifier>
<identifier type="doi">10.18653/v1/2020.repl4nlp-1.11</identifier>
<location>
<url>https://aclanthology.org/2020.repl4nlp-1.11</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>78</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Training with Semantic Role Labeling for Better Generalization in Natural Language Inference
%A Cengiz, Cemil
%A Yuret, Deniz
%Y Gella, Spandana
%Y Welbl, Johannes
%Y Rei, Marek
%Y Petroni, Fabio
%Y Lewis, Patrick
%Y Strubell, Emma
%Y Seo, Minjoon
%Y Hajishirzi, Hannaneh
%S Proceedings of the 5th Workshop on Representation Learning for NLP
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F cengiz-yuret-2020-joint
%X End-to-end models trained on natural language inference (NLI) datasets show low generalization on out-of-distribution evaluation sets. The models tend to learn shallow heuristics due to dataset biases. The performance decreases dramatically on diagnostic sets measuring compositionality or robustness against simple heuristics. Existing solutions for this problem employ dataset augmentation which has the drawbacks of being applicable to only a limited set of adversaries and at worst hurting the model performance on other adversaries not included in the augmentation set. Instead, our proposed solution is to improve sentence understanding (hence out-of-distribution generalization) with joint learning of explicit semantics. We show that a BERT based model trained jointly on English semantic role labeling (SRL) and NLI achieves significantly higher performance on external evaluation sets measuring generalization performance.
%R 10.18653/v1/2020.repl4nlp-1.11
%U https://aclanthology.org/2020.repl4nlp-1.11
%U https://doi.org/10.18653/v1/2020.repl4nlp-1.11
%P 78-88
Markdown (Informal)
[Joint Training with Semantic Role Labeling for Better Generalization in Natural Language Inference](https://aclanthology.org/2020.repl4nlp-1.11) (Cengiz & Yuret, RepL4NLP 2020)
ACL