@inproceedings{verma-etal-2023-comparing,
title = "Comparing and combining some popular {NER} approaches on Biomedical tasks",
author = "Verma, Harsh and
Bergler, Sabine and
Tahaei, Narjesossadat",
editor = "Demner-fushman, Dina and
Ananiadou, Sophia and
Cohen, Kevin",
booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bionlp-1.24",
doi = "10.18653/v1/2023.bionlp-1.24",
pages = "273--279",
abstract = "We compare three simple and popular approaches for NER: 1) SEQ (sequence labeling with a linear token classifier) 2) SeqCRF (sequence labeling with Conditional Random Fields), and 3) SpanPred (span prediction with boundary token embeddings). We compare the approaches on 4 biomedical NER tasks: GENIA, NCBI-Disease, LivingNER (Spanish), and SocialDisNER (Spanish). The SpanPred model demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 1.3 and 0.6 F1 respectively. The SeqCRF model also demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 0.2 F1 and 0.7 respectively. The SEQ model is competitive with the state-of-the-art on LivingNER dataset. We explore some simple ways of combining the three approaches. We find that majority voting consistently gives high precision and high F1 across all 4 datasets. Lastly, we implement a system that learns to combine SEQ{'}s and SpanPred{'}s predictions, generating systems that give high recall and high F1 across all 4 datasets. On the GENIA dataset, we find that our learned combiner system significantly boosts F1(+1.2) and recall(+2.1) over the systems being combined.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verma-etal-2023-comparing">
<titleInfo>
<title>Comparing and combining some popular NER approaches on Biomedical tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harsh</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Bergler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Narjesossadat</namePart>
<namePart type="family">Tahaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We compare three simple and popular approaches for NER: 1) SEQ (sequence labeling with a linear token classifier) 2) SeqCRF (sequence labeling with Conditional Random Fields), and 3) SpanPred (span prediction with boundary token embeddings). We compare the approaches on 4 biomedical NER tasks: GENIA, NCBI-Disease, LivingNER (Spanish), and SocialDisNER (Spanish). The SpanPred model demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 1.3 and 0.6 F1 respectively. The SeqCRF model also demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 0.2 F1 and 0.7 respectively. The SEQ model is competitive with the state-of-the-art on LivingNER dataset. We explore some simple ways of combining the three approaches. We find that majority voting consistently gives high precision and high F1 across all 4 datasets. Lastly, we implement a system that learns to combine SEQ’s and SpanPred’s predictions, generating systems that give high recall and high F1 across all 4 datasets. On the GENIA dataset, we find that our learned combiner system significantly boosts F1(+1.2) and recall(+2.1) over the systems being combined.</abstract>
<identifier type="citekey">verma-etal-2023-comparing</identifier>
<identifier type="doi">10.18653/v1/2023.bionlp-1.24</identifier>
<location>
<url>https://aclanthology.org/2023.bionlp-1.24</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>273</start>
<end>279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing and combining some popular NER approaches on Biomedical tasks
%A Verma, Harsh
%A Bergler, Sabine
%A Tahaei, Narjesossadat
%Y Demner-fushman, Dina
%Y Ananiadou, Sophia
%Y Cohen, Kevin
%S The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F verma-etal-2023-comparing
%X We compare three simple and popular approaches for NER: 1) SEQ (sequence labeling with a linear token classifier) 2) SeqCRF (sequence labeling with Conditional Random Fields), and 3) SpanPred (span prediction with boundary token embeddings). We compare the approaches on 4 biomedical NER tasks: GENIA, NCBI-Disease, LivingNER (Spanish), and SocialDisNER (Spanish). The SpanPred model demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 1.3 and 0.6 F1 respectively. The SeqCRF model also demonstrates state-of-the-art performance on LivingNER and SocialDisNER, improving F1 by 0.2 F1 and 0.7 respectively. The SEQ model is competitive with the state-of-the-art on LivingNER dataset. We explore some simple ways of combining the three approaches. We find that majority voting consistently gives high precision and high F1 across all 4 datasets. Lastly, we implement a system that learns to combine SEQ’s and SpanPred’s predictions, generating systems that give high recall and high F1 across all 4 datasets. On the GENIA dataset, we find that our learned combiner system significantly boosts F1(+1.2) and recall(+2.1) over the systems being combined.
%R 10.18653/v1/2023.bionlp-1.24
%U https://aclanthology.org/2023.bionlp-1.24
%U https://doi.org/10.18653/v1/2023.bionlp-1.24
%P 273-279
Markdown (Informal)
[Comparing and combining some popular NER approaches on Biomedical tasks](https://aclanthology.org/2023.bionlp-1.24) (Verma et al., BioNLP 2023)
ACL