<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cartuyvels-etal-2020-autoregressive">
    <titleInfo>
        <title>Autoregressive Reasoning over Chains of Facts with Transformers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ruben</namePart>
        <namePart type="family">Cartuyvels</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Spinks</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marie-Francine</namePart>
        <namePart type="family">Moens</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 28th International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Donia</namePart>
            <namePart type="family">Scott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nuria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chengqing</namePart>
            <namePart type="family">Zong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources of evidence or facts for multi-hop reasoning becomes increasingly hard when the number of sources needed to make an inference grows. Our algorithm copes with this by decomposing the selection of facts from a corpus autoregressively, conditioning the next iteration on previously selected facts. This allows us to use a pairwise learning-to-rank loss. We validate our method on datasets of the TextGraphs 2019 and 2020 Shared Tasks for explanation regeneration. Existing work on this task either evaluates facts in isolation or artificially limits the possible chains of facts, thus limiting multi-hop inference. We demonstrate that our algorithm, when used with a pre-trained transformer model, outperforms the previous state-of-the-art in terms of precision, training time and inference efficiency.</abstract>
    <identifier type="citekey">cartuyvels-etal-2020-autoregressive</identifier>
    <identifier type="doi">10.18653/v1/2020.coling-main.610</identifier>
    <location>
        <url>https://aclanthology.org/2020.coling-main.610/</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>6916</start>
            <end>6930</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Autoregressive Reasoning over Chains of Facts with Transformers
%A Cartuyvels, Ruben
%A Spinks, Graham
%A Moens, Marie-Francine
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F cartuyvels-etal-2020-autoregressive
%X This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources of evidence or facts for multi-hop reasoning becomes increasingly hard when the number of sources needed to make an inference grows. Our algorithm copes with this by decomposing the selection of facts from a corpus autoregressively, conditioning the next iteration on previously selected facts. This allows us to use a pairwise learning-to-rank loss. We validate our method on datasets of the TextGraphs 2019 and 2020 Shared Tasks for explanation regeneration. Existing work on this task either evaluates facts in isolation or artificially limits the possible chains of facts, thus limiting multi-hop inference. We demonstrate that our algorithm, when used with a pre-trained transformer model, outperforms the previous state-of-the-art in terms of precision, training time and inference efficiency.
%R 10.18653/v1/2020.coling-main.610
%U https://aclanthology.org/2020.coling-main.610/
%U https://doi.org/10.18653/v1/2020.coling-main.610
%P 6916-6930

Markdown (Informal)

[Autoregressive Reasoning over Chains of Facts with Transformers](https://aclanthology.org/2020.coling-main.610/) (Cartuyvels et al., COLING 2020)

• Autoregressive Reasoning over Chains of Facts with Transformers (Cartuyvels et al., COLING 2020)

ACL

• Ruben Cartuyvels, Graham Spinks, and Marie-Francine Moens. 2020. Autoregressive Reasoning over Chains of Facts with Transformers. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6916–6930, Barcelona, Spain (Online). International Committee on Computational Linguistics.