@inproceedings{magnusson-dietz-2019-analysis,
title = "An Analysis of Deep Contextual Word Embeddings and Neural Architectures for Toponym Mention Detection in Scientific Publications",
author = "Magnusson, Matthew and
Dietz, Laura",
editor = "Nastase, Vivi and
Roth, Benjamin and
Dietz, Laura and
McCallum, Andrew",
booktitle = "Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2607",
doi = "10.18653/v1/W19-2607",
pages = "48--56",
abstract = "Toponym detection in scientific papers is an open task and a key first step in place entity enrichment of documents. We examine three common neural architectures in NLP: 1) convolutional neural network, 2) multi-layer perceptron (both applied in a sliding window context) and 3) bidirectional LSTM and apply contextual and non-contextual word embedding layers to these models. We find that deep contextual word embeddings improve the performance of the bi-LSTM with CRF neural architecture achieving the best performance when multiple layers of deep contextual embeddings are concatenated. Our best performing model achieves an average F1 of 0.910 when evaluated on overlap macro exceeding previous state-of-the-art models in the toponym detection task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="magnusson-dietz-2019-analysis">
<titleInfo>
<title>An Analysis of Deep Contextual Word Embeddings and Neural Architectures for Toponym Mention Detection in Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Magnusson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Dietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivi</namePart>
<namePart type="family">Nastase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Dietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Toponym detection in scientific papers is an open task and a key first step in place entity enrichment of documents. We examine three common neural architectures in NLP: 1) convolutional neural network, 2) multi-layer perceptron (both applied in a sliding window context) and 3) bidirectional LSTM and apply contextual and non-contextual word embedding layers to these models. We find that deep contextual word embeddings improve the performance of the bi-LSTM with CRF neural architecture achieving the best performance when multiple layers of deep contextual embeddings are concatenated. Our best performing model achieves an average F1 of 0.910 when evaluated on overlap macro exceeding previous state-of-the-art models in the toponym detection task.</abstract>
<identifier type="citekey">magnusson-dietz-2019-analysis</identifier>
<identifier type="doi">10.18653/v1/W19-2607</identifier>
<location>
<url>https://aclanthology.org/W19-2607</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>48</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Analysis of Deep Contextual Word Embeddings and Neural Architectures for Toponym Mention Detection in Scientific Publications
%A Magnusson, Matthew
%A Dietz, Laura
%Y Nastase, Vivi
%Y Roth, Benjamin
%Y Dietz, Laura
%Y McCallum, Andrew
%S Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F magnusson-dietz-2019-analysis
%X Toponym detection in scientific papers is an open task and a key first step in place entity enrichment of documents. We examine three common neural architectures in NLP: 1) convolutional neural network, 2) multi-layer perceptron (both applied in a sliding window context) and 3) bidirectional LSTM and apply contextual and non-contextual word embedding layers to these models. We find that deep contextual word embeddings improve the performance of the bi-LSTM with CRF neural architecture achieving the best performance when multiple layers of deep contextual embeddings are concatenated. Our best performing model achieves an average F1 of 0.910 when evaluated on overlap macro exceeding previous state-of-the-art models in the toponym detection task.
%R 10.18653/v1/W19-2607
%U https://aclanthology.org/W19-2607
%U https://doi.org/10.18653/v1/W19-2607
%P 48-56
Markdown (Informal)
[An Analysis of Deep Contextual Word Embeddings and Neural Architectures for Toponym Mention Detection in Scientific Publications](https://aclanthology.org/W19-2607) (Magnusson & Dietz, NAACL 2019)
ACL