@inproceedings{knafou-etal-2020-bitem,
title = "{B}i{T}e{M} at {WNUT} 2020 Shared Task-1: Named Entity Recognition over Wet Lab Protocols using an Ensemble of Contextual Language Models",
author = "Knafou, Julien and
Naderi, Nona and
Copara, Jenny and
Teodoro, Douglas and
Ruch, Patrick",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.40",
doi = "10.18653/v1/2020.wnut-1.40",
pages = "305--313",
abstract = "Recent improvements in machine-reading technologies attracted much attention to automation problems and their possibilities. In this context, WNUT 2020 introduces a Name Entity Recognition (NER) task based on wet laboratory procedures. In this paper, we present a 3-step method based on deep neural language models that reported the best overall exact match F1-score (77.99{\%}) of the competition. By fine-tuning 10 times, 10 different pretrained language models, this work shows the advantage of having more models in an ensemble based on a majority of votes strategy. On top of that, having 100 different models allowed us to analyse the combinations of ensemble that demonstrated the impact of having multiple pretrained models versus fine-tuning a pretrained model multiple times.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="knafou-etal-2020-bitem">
<titleInfo>
<title>BiTeM at WNUT 2020 Shared Task-1: Named Entity Recognition over Wet Lab Protocols using an Ensemble of Contextual Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Knafou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nona</namePart>
<namePart type="family">Naderi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jenny</namePart>
<namePart type="family">Copara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Teodoro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Ruch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent improvements in machine-reading technologies attracted much attention to automation problems and their possibilities. In this context, WNUT 2020 introduces a Name Entity Recognition (NER) task based on wet laboratory procedures. In this paper, we present a 3-step method based on deep neural language models that reported the best overall exact match F1-score (77.99%) of the competition. By fine-tuning 10 times, 10 different pretrained language models, this work shows the advantage of having more models in an ensemble based on a majority of votes strategy. On top of that, having 100 different models allowed us to analyse the combinations of ensemble that demonstrated the impact of having multiple pretrained models versus fine-tuning a pretrained model multiple times.</abstract>
<identifier type="citekey">knafou-etal-2020-bitem</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.40</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.40</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>305</start>
<end>313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BiTeM at WNUT 2020 Shared Task-1: Named Entity Recognition over Wet Lab Protocols using an Ensemble of Contextual Language Models
%A Knafou, Julien
%A Naderi, Nona
%A Copara, Jenny
%A Teodoro, Douglas
%A Ruch, Patrick
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F knafou-etal-2020-bitem
%X Recent improvements in machine-reading technologies attracted much attention to automation problems and their possibilities. In this context, WNUT 2020 introduces a Name Entity Recognition (NER) task based on wet laboratory procedures. In this paper, we present a 3-step method based on deep neural language models that reported the best overall exact match F1-score (77.99%) of the competition. By fine-tuning 10 times, 10 different pretrained language models, this work shows the advantage of having more models in an ensemble based on a majority of votes strategy. On top of that, having 100 different models allowed us to analyse the combinations of ensemble that demonstrated the impact of having multiple pretrained models versus fine-tuning a pretrained model multiple times.
%R 10.18653/v1/2020.wnut-1.40
%U https://aclanthology.org/2020.wnut-1.40
%U https://doi.org/10.18653/v1/2020.wnut-1.40
%P 305-313
Markdown (Informal)
[BiTeM at WNUT 2020 Shared Task-1: Named Entity Recognition over Wet Lab Protocols using an Ensemble of Contextual Language Models](https://aclanthology.org/2020.wnut-1.40) (Knafou et al., WNUT 2020)
ACL