<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dankers-titov-2022-recursive">
    <titleInfo>
        <title>Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Verna</namePart>
        <namePart type="family">Dankers</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Titov</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>A recent line of work in NLP focuses on the (dis)ability of models to generalise compositionally for artificial languages. However, when considering natural language tasks, the data involved is not strictly, or locally, compositional. Quantifying the compositionality of data is a challenging task, which has been investigated primarily for short utterances. We use recursive neural models (Tree-LSTMs) with bottlenecks that limit the transfer of information between nodes. We illustrate that comparing data’s representations in models with and without the bottleneck can be used to produce a compositionality metric. The procedure is applied to the evaluation of arithmetic expressions using synthetic data, and sentiment classification using natural language data. We demonstrate that compression through a bottleneck impacts non-compositional examples disproportionatelyand then use the bottleneck compositionality metric (BCM) to distinguish compositional from non-compositional samples, yielding a compositionality ranking over a dataset.</abstract>
    <identifier type="citekey">dankers-titov-2022-recursive</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.320</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.320</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>4361</start>
            <end>4378</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality
%A Dankers, Verna
%A Titov, Ivan
%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 dankers-titov-2022-recursive
%X A recent line of work in NLP focuses on the (dis)ability of models to generalise compositionally for artificial languages. However, when considering natural language tasks, the data involved is not strictly, or locally, compositional. Quantifying the compositionality of data is a challenging task, which has been investigated primarily for short utterances. We use recursive neural models (Tree-LSTMs) with bottlenecks that limit the transfer of information between nodes. We illustrate that comparing data’s representations in models with and without the bottleneck can be used to produce a compositionality metric. The procedure is applied to the evaluation of arithmetic expressions using synthetic data, and sentiment classification using natural language data. We demonstrate that compression through a bottleneck impacts non-compositional examples disproportionatelyand then use the bottleneck compositionality metric (BCM) to distinguish compositional from non-compositional samples, yielding a compositionality ranking over a dataset.
%R 10.18653/v1/2022.findings-emnlp.320
%U https://aclanthology.org/2022.findings-emnlp.320
%U https://doi.org/10.18653/v1/2022.findings-emnlp.320
%P 4361-4378

Markdown (Informal)

[Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality](https://aclanthology.org/2022.findings-emnlp.320) (Dankers & Titov, Findings 2022)

• Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality (Dankers & Titov, Findings 2022)

ACL

• Verna Dankers and Ivan Titov. 2022. Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4361–4378, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.