<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2023-scene">
    <titleInfo>
        <title>SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Deqing</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ameya</namePart>
        <namePart type="family">Godbole</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Robin</namePart>
        <namePart type="family">Jia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Detecting negatives (such as non-entailment relationships, unanswerable questions, and false claims) is an important and challenging aspect of many natural language understanding tasks. Though manually collecting challenging negative examples can help models detect them, it is both costly and domain-specific. In this work, we propose Self-labeled Counterfactuals for Extrapolating to Negative Examples (SCENE), an automatic method for synthesizing training data that greatly improves models’ ability to detect challenging negative examples. In contrast with standard data augmentation, which synthesizes new examples for existing labels, SCENE can synthesize negative examples zero-shot from only positive ones. Given a positive example, SCENE perturbs it with a mask infilling model, then determines whether the resulting example is negative based on a self-training heuristic. With access to only answerable training examples, SCENE can close 69.6% of the performance gap on SQuAD 2.0, a dataset where half of the evaluation examples are unanswerable, compared to a model trained on SQuAD 2.0. Our method also extends to boolean question answering and recognizing textual entailment, and improves generalization from SQuAD to ACE-whQA, an out-of-domain extractive QA benchmark.</abstract>
    <identifier type="citekey">fu-etal-2023-scene</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.485</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.485</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>7832</start>
            <end>7848</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples
%A Fu, Deqing
%A Godbole, Ameya
%A Jia, Robin
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F fu-etal-2023-scene
%X Detecting negatives (such as non-entailment relationships, unanswerable questions, and false claims) is an important and challenging aspect of many natural language understanding tasks. Though manually collecting challenging negative examples can help models detect them, it is both costly and domain-specific. In this work, we propose Self-labeled Counterfactuals for Extrapolating to Negative Examples (SCENE), an automatic method for synthesizing training data that greatly improves models’ ability to detect challenging negative examples. In contrast with standard data augmentation, which synthesizes new examples for existing labels, SCENE can synthesize negative examples zero-shot from only positive ones. Given a positive example, SCENE perturbs it with a mask infilling model, then determines whether the resulting example is negative based on a self-training heuristic. With access to only answerable training examples, SCENE can close 69.6% of the performance gap on SQuAD 2.0, a dataset where half of the evaluation examples are unanswerable, compared to a model trained on SQuAD 2.0. Our method also extends to boolean question answering and recognizing textual entailment, and improves generalization from SQuAD to ACE-whQA, an out-of-domain extractive QA benchmark.
%R 10.18653/v1/2023.emnlp-main.485
%U https://aclanthology.org/2023.emnlp-main.485
%U https://doi.org/10.18653/v1/2023.emnlp-main.485
%P 7832-7848

Markdown (Informal)

[SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples](https://aclanthology.org/2023.emnlp-main.485) (Fu et al., EMNLP 2023)

• SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples (Fu et al., EMNLP 2023)

ACL

• Deqing Fu, Ameya Godbole, and Robin Jia. 2023. SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7832–7848, Singapore. Association for Computational Linguistics.