@inproceedings{sohrab-etal-2019-neural,
title = "A Neural Pipeline Approach for the {P}harma{C}o{NER} Shared Task using Contextual Exhaustive Models",
author = "Sohrab, Mohammad Golam and
Pham, Minh Thang and
Miwa, Makoto and
Takamura, Hiroya",
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/D19-5708",
doi = "10.18653/v1/D19-5708",
pages = "47--55",
abstract = "We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities. We proposed a neural NER model that captures the surrounding semantic information of a given sequence by capturing the forward- and backward-context of bidirectional LSTM (Bi-LSTM) output of a target span using contextual span representation-based exhaustive approach. The NER model enumerates all possible spans as potential entity mentions and classify them into entity types or no entity with deep neural networks. For representing span, we compare several different neural network architectures and their ensembling for the NER model. We then perform dictionary matching for CI and, if there is no matching, we further compute similarity scores between a mention and CUIs using entity embeddings to assign the CUI with the highest score to the mention. We evaluate our approach on the two sub-tasks in the shared task. Among the five submitted runs, the best run for each sub-task achieved the F-score of 86.76{\%} on Sub-task 1 (NER) and the F-score of 79.97{\%} (strict) on Sub-task 2 (CI).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sohrab-etal-2019-neural">
<titleInfo>
<title>A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Golam</namePart>
<namePart type="family">Sohrab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Thang</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</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>We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities. We proposed a neural NER model that captures the surrounding semantic information of a given sequence by capturing the forward- and backward-context of bidirectional LSTM (Bi-LSTM) output of a target span using contextual span representation-based exhaustive approach. The NER model enumerates all possible spans as potential entity mentions and classify them into entity types or no entity with deep neural networks. For representing span, we compare several different neural network architectures and their ensembling for the NER model. We then perform dictionary matching for CI and, if there is no matching, we further compute similarity scores between a mention and CUIs using entity embeddings to assign the CUI with the highest score to the mention. We evaluate our approach on the two sub-tasks in the shared task. Among the five submitted runs, the best run for each sub-task achieved the F-score of 86.76% on Sub-task 1 (NER) and the F-score of 79.97% (strict) on Sub-task 2 (CI).</abstract>
<identifier type="citekey">sohrab-etal-2019-neural</identifier>
<identifier type="doi">10.18653/v1/D19-5708</identifier>
<location>
<url>https://aclanthology.org/D19-5708</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>47</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models
%A Sohrab, Mohammad Golam
%A Pham, Minh Thang
%A Miwa, Makoto
%A Takamura, Hiroya
%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 sohrab-etal-2019-neural
%X We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities. We proposed a neural NER model that captures the surrounding semantic information of a given sequence by capturing the forward- and backward-context of bidirectional LSTM (Bi-LSTM) output of a target span using contextual span representation-based exhaustive approach. The NER model enumerates all possible spans as potential entity mentions and classify them into entity types or no entity with deep neural networks. For representing span, we compare several different neural network architectures and their ensembling for the NER model. We then perform dictionary matching for CI and, if there is no matching, we further compute similarity scores between a mention and CUIs using entity embeddings to assign the CUI with the highest score to the mention. We evaluate our approach on the two sub-tasks in the shared task. Among the five submitted runs, the best run for each sub-task achieved the F-score of 86.76% on Sub-task 1 (NER) and the F-score of 79.97% (strict) on Sub-task 2 (CI).
%R 10.18653/v1/D19-5708
%U https://aclanthology.org/D19-5708
%U https://doi.org/10.18653/v1/D19-5708
%P 47-55
Markdown (Informal)
[A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models](https://aclanthology.org/D19-5708) (Sohrab et al., BioNLP 2019)
ACL