<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zanzotto-etal-2020-kermit">
    <titleInfo>
        <title>KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Fabio</namePart>
        <namePart type="given">Massimo</namePart>
        <namePart type="family">Zanzotto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="family">Santilli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Leonardo</namePart>
        <namePart type="family">Ranaldi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dario</namePart>
        <namePart type="family">Onorati</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pierfrancesco</namePart>
        <namePart type="family">Tommasino</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Francesca</namePart>
        <namePart type="family">Fallucchi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality in downstream tasks due to the success of large-scale textual representation learners. In this paper, we propose KERMIT (Kernel-inspired Encoder with Recursive Mechanism for Interpretable Trees) to embed symbolic syntactic parse trees into artificial neural networks and to visualize how syntax is used in inference. We experimented with KERMIT paired with two state-of-the-art transformer-based universal sentence encoders (BERT and XLNet) and we showed that KERMIT can indeed boost their performance by effectively embedding human-coded universal syntactic representations in neural networks</abstract>
    <identifier type="citekey">zanzotto-etal-2020-kermit</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.18</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.18</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>256</start>
            <end>267</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations
%A Zanzotto, Fabio Massimo
%A Santilli, Andrea
%A Ranaldi, Leonardo
%A Onorati, Dario
%A Tommasino, Pierfrancesco
%A Fallucchi, Francesca
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zanzotto-etal-2020-kermit
%X Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality in downstream tasks due to the success of large-scale textual representation learners. In this paper, we propose KERMIT (Kernel-inspired Encoder with Recursive Mechanism for Interpretable Trees) to embed symbolic syntactic parse trees into artificial neural networks and to visualize how syntax is used in inference. We experimented with KERMIT paired with two state-of-the-art transformer-based universal sentence encoders (BERT and XLNet) and we showed that KERMIT can indeed boost their performance by effectively embedding human-coded universal syntactic representations in neural networks
%R 10.18653/v1/2020.emnlp-main.18
%U https://aclanthology.org/2020.emnlp-main.18
%U https://doi.org/10.18653/v1/2020.emnlp-main.18
%P 256-267

Markdown (Informal)

[KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations](https://aclanthology.org/2020.emnlp-main.18) (Zanzotto et al., EMNLP 2020)

• KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations (Zanzotto et al., EMNLP 2020)

ACL

• Fabio Massimo Zanzotto, Andrea Santilli, Leonardo Ranaldi, Dario Onorati, Pierfrancesco Tommasino, and Francesca Fallucchi. 2020. KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 256–267, Online. Association for Computational Linguistics.