<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berlanga-neto-ruiz-2021-split">
    <titleInfo>
        <title>Split-and-Rephrase in a Cross-Lingual Manner: A Complete Pipeline</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Paulo</namePart>
        <namePart type="family">Berlanga Neto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Evandro</namePart>
        <namePart type="given">Eduardo</namePart>
        <namePart type="given">Seron</namePart>
        <namePart type="family">Ruiz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Held Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Split-and-rephrase is a challenging task that promotes the transformation of a given complex input sentence into multiple shorter sentences retaining equivalent meaning. This rewriting approach conceptualizes that shorter sentences benefit human readers and improve NLP downstream tasks attending as a preprocessing step. This work presents a complete pipeline capable of performing the split-and-rephrase method in a cross-lingual manner. We trained sequence-to-sequence neural models as from English corpora and applied them to predict the transformations in English and Brazilian Portuguese sentences jointly with BERT’s masked language modeling. Contrary to traditional approaches that seek training models with extensive vocabularies, we present a non-trivial way to construct symbolic ones generalized solely by grammatical classes (POS tags) and their respective recurrences, reducing the amount of necessary training data. This pipeline contribution showed competitive results encouraging the expansion of the method to languages other than English.</abstract>
    <identifier type="citekey">berlanga-neto-ruiz-2021-split</identifier>
    <location>
        <url>https://aclanthology.org/2021.ranlp-1.19</url>
    </location>
    <part>
        <date>2021-09</date>
        <extent unit="page">
            <start>155</start>
            <end>164</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Split-and-Rephrase in a Cross-Lingual Manner: A Complete Pipeline
%A Berlanga Neto, Paulo
%A Ruiz, Evandro Eduardo Seron
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F berlanga-neto-ruiz-2021-split
%X Split-and-rephrase is a challenging task that promotes the transformation of a given complex input sentence into multiple shorter sentences retaining equivalent meaning. This rewriting approach conceptualizes that shorter sentences benefit human readers and improve NLP downstream tasks attending as a preprocessing step. This work presents a complete pipeline capable of performing the split-and-rephrase method in a cross-lingual manner. We trained sequence-to-sequence neural models as from English corpora and applied them to predict the transformations in English and Brazilian Portuguese sentences jointly with BERT’s masked language modeling. Contrary to traditional approaches that seek training models with extensive vocabularies, we present a non-trivial way to construct symbolic ones generalized solely by grammatical classes (POS tags) and their respective recurrences, reducing the amount of necessary training data. This pipeline contribution showed competitive results encouraging the expansion of the method to languages other than English.
%U https://aclanthology.org/2021.ranlp-1.19
%P 155-164

Markdown (Informal)

[Split-and-Rephrase in a Cross-Lingual Manner: A Complete Pipeline](https://aclanthology.org/2021.ranlp-1.19) (Berlanga Neto & Ruiz, RANLP 2021)

• Split-and-Rephrase in a Cross-Lingual Manner: A Complete Pipeline (Berlanga Neto & Ruiz, RANLP 2021)

ACL

• Paulo Berlanga Neto and Evandro Eduardo Seron Ruiz. 2021. Split-and-Rephrase in a Cross-Lingual Manner: A Complete Pipeline. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 155–164, Held Online. INCOMA Ltd..