<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sadat-caragea-2022-learning">
    <titleInfo>
        <title>Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mobashir</namePart>
        <namePart type="family">Sadat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cornelia</namePart>
        <namePart type="family">Caragea</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>Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) aims at predicting the relation between a pair of sentences (premise and hypothesis) as entailment, contradiction or semantic independence. Although deep learning models have shown promising performance for NLI in recent years, they rely on large scale expensive human-annotated datasets. Semi-supervised learning (SSL) is a popular technique for reducing the reliance on human annotation by leveraging unlabeled data for training. However, despite its substantial success on single sentence classification tasks where the challenge in making use of unlabeled data is to assign “good enough” pseudo-labels, for NLI tasks, the nature of unlabeled data is more complex: one of the sentences in the pair (usually the hypothesis) along with the class label are missing from the data and require human annotations, which makes SSL for NLI more challenging. In this paper, we propose a novel way to incorporate unlabeled data in SSL for NLI where we use a conditional language model, BART to generate the hypotheses for the unlabeled sentences (used as premises). Our experiments show that our SSL framework successfully exploits unlabeled data and substantially improves the performance of four NLI datasets in low-resource settings. We release our code here: https://github.com/msadat3/SSL_for_NLI</abstract>
    <identifier type="citekey">sadat-caragea-2022-learning</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.351</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.351</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>4763</start>
            <end>4776</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference
%A Sadat, Mobashir
%A Caragea, Cornelia
%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 sadat-caragea-2022-learning
%X Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) aims at predicting the relation between a pair of sentences (premise and hypothesis) as entailment, contradiction or semantic independence. Although deep learning models have shown promising performance for NLI in recent years, they rely on large scale expensive human-annotated datasets. Semi-supervised learning (SSL) is a popular technique for reducing the reliance on human annotation by leveraging unlabeled data for training. However, despite its substantial success on single sentence classification tasks where the challenge in making use of unlabeled data is to assign “good enough” pseudo-labels, for NLI tasks, the nature of unlabeled data is more complex: one of the sentences in the pair (usually the hypothesis) along with the class label are missing from the data and require human annotations, which makes SSL for NLI more challenging. In this paper, we propose a novel way to incorporate unlabeled data in SSL for NLI where we use a conditional language model, BART to generate the hypotheses for the unlabeled sentences (used as premises). Our experiments show that our SSL framework successfully exploits unlabeled data and substantially improves the performance of four NLI datasets in low-resource settings. We release our code here: https://github.com/msadat3/SSL_for_NLI
%R 10.18653/v1/2022.findings-emnlp.351
%U https://aclanthology.org/2022.findings-emnlp.351
%U https://doi.org/10.18653/v1/2022.findings-emnlp.351
%P 4763-4776

Markdown (Informal)

[Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference](https://aclanthology.org/2022.findings-emnlp.351) (Sadat & Caragea, Findings 2022)

• Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference (Sadat & Caragea, Findings 2022)

ACL

• Mobashir Sadat and Cornelia Caragea. 2022. Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4763–4776, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.