<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="geva-etal-2021-whats">
    <titleInfo>
        <title>What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mor</namePart>
        <namePart type="family">Geva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Uri</namePart>
        <namePart type="family">Katz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aviv</namePart>
        <namePart type="family">Ben-Arie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Berant</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 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The primary paradigm for multi-task training in natural language processing is to represent the input with a shared pre-trained language model, and add a small, thin network (head) per task. Given an input, a target head is the head that is selected for outputting the final prediction. In this work, we examine the behaviour of non-target heads, that is, the output of heads when given input that belongs to a different task than the one they were trained for. We find that non-target heads exhibit emergent behaviour, which may either explain the target task, or generalize beyond their original task. For example, in a numerical reasoning task, a span extraction head extracts from the input the arguments to a computation that results in a number generated by a target generative head. In addition, a summarization head that is trained with a target question answering head, outputs query-based summaries when given a question and a context from which the answer is to be extracted. This emergent behaviour suggests that multi-task training leads to non-trivial extrapolation of skills, which can be harnessed for interpretability and generalization.</abstract>
    <identifier type="citekey">geva-etal-2021-whats</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.646</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.646</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>8201</start>
            <end>8215</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models
%A Geva, Mor
%A Katz, Uri
%A Ben-Arie, Aviv
%A Berant, Jonathan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F geva-etal-2021-whats
%X The primary paradigm for multi-task training in natural language processing is to represent the input with a shared pre-trained language model, and add a small, thin network (head) per task. Given an input, a target head is the head that is selected for outputting the final prediction. In this work, we examine the behaviour of non-target heads, that is, the output of heads when given input that belongs to a different task than the one they were trained for. We find that non-target heads exhibit emergent behaviour, which may either explain the target task, or generalize beyond their original task. For example, in a numerical reasoning task, a span extraction head extracts from the input the arguments to a computation that results in a number generated by a target generative head. In addition, a summarization head that is trained with a target question answering head, outputs query-based summaries when given a question and a context from which the answer is to be extracted. This emergent behaviour suggests that multi-task training leads to non-trivial extrapolation of skills, which can be harnessed for interpretability and generalization.
%R 10.18653/v1/2021.emnlp-main.646
%U https://aclanthology.org/2021.emnlp-main.646
%U https://doi.org/10.18653/v1/2021.emnlp-main.646
%P 8201-8215

Markdown (Informal)

[What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models](https://aclanthology.org/2021.emnlp-main.646) (Geva et al., EMNLP 2021)

• What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models (Geva et al., EMNLP 2021)

ACL

• Mor Geva, Uri Katz, Aviv Ben-Arie, and Jonathan Berant. 2021. What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8201–8215, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.