@inproceedings{lahuerta-etal-2019-ixamed,
title = "{I}xa{M}ed at {P}harmaco{NER} Challenge 2019",
author = "Lahuerta, Xabier and
Goenaga, Iakes and
Gojenola, Koldo and
Atutxa Salazar, Aitziber and
Oronoz, Maite",
editor = "Jin-Dong, Kim and
Claire, N{\'e}dellec and
Robert, Bossy and
Louise, Del{\'e}ger",
booktitle = "Proceedings of the 5th Workshop on BioNLP Open Shared Tasks",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5704",
doi = "10.18653/v1/D19-5704",
pages = "21--25",
abstract = "The aim of this paper is to present our approach (IxaMed) in the PharmacoNER 2019 task. The task consists of identifying chemical, drug, and gene/protein mentions from clinical case studies written in Spanish. The evaluation of the task is divided in two scenarios: one corresponding to the detection of named entities and one corresponding to the indexation of named entities that have been previously identified. In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings. We have achieved our best result (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records (50M words) with contextual string embeddings of Wikipedia and Electronic Health Records. On the other hand, for the indexation of the named entities we have used the Levenshtein distance obtaining a 85.34 F-Score as our best result.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lahuerta-etal-2019-ixamed">
<titleInfo>
<title>IxaMed at PharmacoNER Challenge 2019</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Lahuerta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iakes</namePart>
<namePart type="family">Goenaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koldo</namePart>
<namePart type="family">Gojenola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitziber</namePart>
<namePart type="family">Atutxa Salazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Oronoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on BioNLP Open Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="family">Jin-Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nédellec</namePart>
<namePart type="family">Claire</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bossy</namePart>
<namePart type="family">Robert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deléger</namePart>
<namePart type="family">Louise</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The aim of this paper is to present our approach (IxaMed) in the PharmacoNER 2019 task. The task consists of identifying chemical, drug, and gene/protein mentions from clinical case studies written in Spanish. The evaluation of the task is divided in two scenarios: one corresponding to the detection of named entities and one corresponding to the indexation of named entities that have been previously identified. In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings. We have achieved our best result (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records (50M words) with contextual string embeddings of Wikipedia and Electronic Health Records. On the other hand, for the indexation of the named entities we have used the Levenshtein distance obtaining a 85.34 F-Score as our best result.</abstract>
<identifier type="citekey">lahuerta-etal-2019-ixamed</identifier>
<identifier type="doi">10.18653/v1/D19-5704</identifier>
<location>
<url>https://aclanthology.org/D19-5704</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>21</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IxaMed at PharmacoNER Challenge 2019
%A Lahuerta, Xabier
%A Goenaga, Iakes
%A Gojenola, Koldo
%A Atutxa Salazar, Aitziber
%A Oronoz, Maite
%Y Jin-Dong, Kim
%Y Claire, Nédellec
%Y Robert, Bossy
%Y Louise, Deléger
%S Proceedings of the 5th Workshop on BioNLP Open Shared Tasks
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F lahuerta-etal-2019-ixamed
%X The aim of this paper is to present our approach (IxaMed) in the PharmacoNER 2019 task. The task consists of identifying chemical, drug, and gene/protein mentions from clinical case studies written in Spanish. The evaluation of the task is divided in two scenarios: one corresponding to the detection of named entities and one corresponding to the indexation of named entities that have been previously identified. In order to identify named entities we have made use of a Bi-LSTM with a CRF on top in combination with different types of word embeddings. We have achieved our best result (86.81 F-Score) combining pretrained word embeddings of Wikipedia and Electronic Health Records (50M words) with contextual string embeddings of Wikipedia and Electronic Health Records. On the other hand, for the indexation of the named entities we have used the Levenshtein distance obtaining a 85.34 F-Score as our best result.
%R 10.18653/v1/D19-5704
%U https://aclanthology.org/D19-5704
%U https://doi.org/10.18653/v1/D19-5704
%P 21-25
Markdown (Informal)
[IxaMed at PharmacoNER Challenge 2019](https://aclanthology.org/D19-5704) (Lahuerta et al., BioNLP 2019)
ACL
- Xabier Lahuerta, Iakes Goenaga, Koldo Gojenola, Aitziber Atutxa Salazar, and Maite Oronoz. 2019. IxaMed at PharmacoNER Challenge 2019. In Proceedings of the 5th Workshop on BioNLP Open Shared Tasks, pages 21–25, Hong Kong, China. Association for Computational Linguistics.