<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="helwe-etal-2022-tina">
    <titleInfo>
        <title>TINA: Textual Inference with Negation Augmentation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chadi</namePart>
        <namePart type="family">Helwe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Simon</namePart>
        <namePart type="family">Coumes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chloé</namePart>
        <namePart type="family">Clavel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fabian</namePart>
        <namePart type="family">Suchanek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Transformer-based language models achieve state-of-the-art results on several natural language processing tasks. One of these is textual entailment, i.e., the task of determining whether a premise logically entails a hypothesis. However, the models perform poorly on this task when the examples contain negations. In this paper, we propose a new definition of textual entailment that captures also negation. This allows us to develop TINA (Textual Inference with Negation Augmentation), a principled technique for negated data augmentation that can be combined with the unlikelihood loss function. Our experiments with different transformer-based models show that our method can significantly improve the performance of the models on textual entailment datasets with negation – without sacrificing performance on datasets without negation.</abstract>
    <identifier type="citekey">helwe-etal-2022-tina</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.301</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.301</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>4086</start>
            <end>4099</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TINA: Textual Inference with Negation Augmentation
%A Helwe, Chadi
%A Coumes, Simon
%A Clavel, Chloé
%A Suchanek, Fabian
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F helwe-etal-2022-tina
%X Transformer-based language models achieve state-of-the-art results on several natural language processing tasks. One of these is textual entailment, i.e., the task of determining whether a premise logically entails a hypothesis. However, the models perform poorly on this task when the examples contain negations. In this paper, we propose a new definition of textual entailment that captures also negation. This allows us to develop TINA (Textual Inference with Negation Augmentation), a principled technique for negated data augmentation that can be combined with the unlikelihood loss function. Our experiments with different transformer-based models show that our method can significantly improve the performance of the models on textual entailment datasets with negation – without sacrificing performance on datasets without negation.
%R 10.18653/v1/2022.findings-emnlp.301
%U https://aclanthology.org/2022.findings-emnlp.301
%U https://doi.org/10.18653/v1/2022.findings-emnlp.301
%P 4086-4099

Markdown (Informal)

[TINA: Textual Inference with Negation Augmentation](https://aclanthology.org/2022.findings-emnlp.301) (Helwe et al., Findings 2022)

• TINA: Textual Inference with Negation Augmentation (Helwe et al., Findings 2022)

ACL

• Chadi Helwe, Simon Coumes, Chloé Clavel, and Fabian Suchanek. 2022. TINA: Textual Inference with Negation Augmentation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4086–4099, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.