@inproceedings{rychlikowski-etal-2021-named,
title = "Named Entity Recognition and Linking Augmented with Large-Scale Structured Data",
author = "Rychlikowski, Pawe{\l} and
Najdecki, Bart{\l}omiej and
Lancucki, Adrian and
Kaczmarek, Adam",
editor = "Babych, Bogdan and
Kanishcheva, Olga and
Nakov, Preslav and
Piskorski, Jakub and
Pivovarova, Lidia and
Starko, Vasyl and
Steinberger, Josef and
Yangarber, Roman and
Marci{\'n}czuk, Micha{\l} and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Robnik-{\v{S}}ikonja, Marko",
booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bsnlp-1.14/",
pages = "115--121",
abstract = "In this paper we describe our submissions to the 2nd and 3rd SlavNER Shared Tasks held at BSNLP 2019 and BSNLP 2021, respectively. The tasks focused on the analysis of Named Entities in multilingual Web documents in Slavic languages with rich inflection. Our solution takes advantage of large collections of both unstructured and structured documents. The former serve as data for unsupervised training of language models and embeddings of lexical units. The latter refers to Wikipedia and its structured counterpart - Wikidata, our source of lemmatization rules, and real-world entities. With the aid of those resources, our system could recognize, normalize and link entities, while being trained with only small amounts of labeled data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rychlikowski-etal-2021-named">
<titleInfo>
<title>Named Entity Recognition and Linking Augmented with Large-Scale Structured Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Rychlikowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bartłomiej</namePart>
<namePart type="family">Najdecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Lancucki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Kaczmarek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kanishcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasyl</namePart>
<namePart type="family">Starko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Robnik-Šikonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kiyv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we describe our submissions to the 2nd and 3rd SlavNER Shared Tasks held at BSNLP 2019 and BSNLP 2021, respectively. The tasks focused on the analysis of Named Entities in multilingual Web documents in Slavic languages with rich inflection. Our solution takes advantage of large collections of both unstructured and structured documents. The former serve as data for unsupervised training of language models and embeddings of lexical units. The latter refers to Wikipedia and its structured counterpart - Wikidata, our source of lemmatization rules, and real-world entities. With the aid of those resources, our system could recognize, normalize and link entities, while being trained with only small amounts of labeled data.</abstract>
<identifier type="citekey">rychlikowski-etal-2021-named</identifier>
<location>
<url>https://aclanthology.org/2021.bsnlp-1.14/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>115</start>
<end>121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition and Linking Augmented with Large-Scale Structured Data
%A Rychlikowski, Paweł
%A Najdecki, Bartłomiej
%A Lancucki, Adrian
%A Kaczmarek, Adam
%Y Babych, Bogdan
%Y Kanishcheva, Olga
%Y Nakov, Preslav
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Starko, Vasyl
%Y Steinberger, Josef
%Y Yangarber, Roman
%Y Marcińczuk, Michał
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Robnik-Šikonja, Marko
%S Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kiyv, Ukraine
%F rychlikowski-etal-2021-named
%X In this paper we describe our submissions to the 2nd and 3rd SlavNER Shared Tasks held at BSNLP 2019 and BSNLP 2021, respectively. The tasks focused on the analysis of Named Entities in multilingual Web documents in Slavic languages with rich inflection. Our solution takes advantage of large collections of both unstructured and structured documents. The former serve as data for unsupervised training of language models and embeddings of lexical units. The latter refers to Wikipedia and its structured counterpart - Wikidata, our source of lemmatization rules, and real-world entities. With the aid of those resources, our system could recognize, normalize and link entities, while being trained with only small amounts of labeled data.
%U https://aclanthology.org/2021.bsnlp-1.14/
%P 115-121
Markdown (Informal)
[Named Entity Recognition and Linking Augmented with Large-Scale Structured Data](https://aclanthology.org/2021.bsnlp-1.14/) (Rychlikowski et al., BSNLP 2021)
ACL