<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-vries-etal-2020-whats">
    <titleInfo>
        <title>What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wietse</namePart>
        <namePart type="family">de Vries</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andreas</namePart>
        <namePart type="family">van Cranenburgh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Malvina</namePart>
        <namePart type="family">Nissim</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <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>Peeking into the inner workings of BERT has shown that its layers resemble the classical NLP pipeline, with progressively more complex tasks being concentrated in later layers. To investigate to what extent these results also hold for a language other than English, we probe a Dutch BERT-based model and the multilingual BERT model for Dutch NLP tasks. In addition, through a deeper analysis of part-of-speech tagging, we show that also within a given task, information is spread over different parts of the network and the pipeline might not be as neat as it seems. Each layer has different specialisations, so that it may be more useful to combine information from different layers, instead of selecting a single one based on the best overall performance.</abstract>
    <identifier type="citekey">de-vries-etal-2020-whats</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.389</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.389</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>4339</start>
            <end>4350</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models
%A de Vries, Wietse
%A van Cranenburgh, Andreas
%A Nissim, Malvina
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F de-vries-etal-2020-whats
%X Peeking into the inner workings of BERT has shown that its layers resemble the classical NLP pipeline, with progressively more complex tasks being concentrated in later layers. To investigate to what extent these results also hold for a language other than English, we probe a Dutch BERT-based model and the multilingual BERT model for Dutch NLP tasks. In addition, through a deeper analysis of part-of-speech tagging, we show that also within a given task, information is spread over different parts of the network and the pipeline might not be as neat as it seems. Each layer has different specialisations, so that it may be more useful to combine information from different layers, instead of selecting a single one based on the best overall performance.
%R 10.18653/v1/2020.findings-emnlp.389
%U https://aclanthology.org/2020.findings-emnlp.389
%U https://doi.org/10.18653/v1/2020.findings-emnlp.389
%P 4339-4350

Markdown (Informal)

[What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models](https://aclanthology.org/2020.findings-emnlp.389) (de Vries et al., Findings 2020)

• What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models (de Vries et al., Findings 2020)

ACL

• Wietse de Vries, Andreas van Cranenburgh, and Malvina Nissim. 2020. What’s so special about BERT’s layers? A closer look at the NLP pipeline in monolingual and multilingual models. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4339–4350, Online. Association for Computational Linguistics.