Proceedings of the 13th International Workshop on Semantic Evaluation 2019
DOI: 10.18653/v1/s19-2230
|View full text |Cite
|
Sign up to set email alerts
|

UNH at SemEval-2019 Task 12: Toponym Resolution in Scientific Papers

Abstract: The SemEval-2019 Task 12 is toponym resolution in scientific papers. We focus on Subtask 1: Toponym Detection which is the identification of spans of text for place names mentioned in a document. We propose two methods: 1) sliding window convolutional neural network using ELMo embeddings (CNN-ELMo), and 2) sliding window multi-Layer perceptron using ELMo embeddings (MLP-ELMo). We also submit a bi-directional LSTM with Conditional Random Fields (bi-LSTM) as a strong baseline given its stateof-art performance in… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2020
2020
2020
2020

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 10 publications
0
2
0
Order By: Relevance
“…Network Architecture There are two paradigms governing the network architectures used for this task: namely, whether localized contextual information is enough, or all available contextual information should be taken into account when making predictions. The former leads to models that only have access to a sliding window of information such as CNNs or MLPs (Magge et al, 2018;Davari et al, 2019;Magnusson and Dietz, 2019). The latter leads to sequential models operating at the sentence level; among which the BiLSTM-CRF architecture is the most favored and provides state-of-the-art results Yadav et al, 2019;Qi et al, 2019;Magnusson and Dietz, 2019).…”
Section: Linguistic Features Previous Work On Toponym Detection In the Medical Domain Have Typically Taken Advantage Of Handcrafted Featumentioning
confidence: 99%
See 1 more Smart Citation
“…Network Architecture There are two paradigms governing the network architectures used for this task: namely, whether localized contextual information is enough, or all available contextual information should be taken into account when making predictions. The former leads to models that only have access to a sliding window of information such as CNNs or MLPs (Magge et al, 2018;Davari et al, 2019;Magnusson and Dietz, 2019). The latter leads to sequential models operating at the sentence level; among which the BiLSTM-CRF architecture is the most favored and provides state-of-the-art results Yadav et al, 2019;Qi et al, 2019;Magnusson and Dietz, 2019).…”
Section: Linguistic Features Previous Work On Toponym Detection In the Medical Domain Have Typically Taken Advantage Of Handcrafted Featumentioning
confidence: 99%
“…The former leads to models that only have access to a sliding window of information such as CNNs or MLPs (Magge et al, 2018;Davari et al, 2019;Magnusson and Dietz, 2019). The latter leads to sequential models operating at the sentence level; among which the BiLSTM-CRF architecture is the most favored and provides state-of-the-art results Yadav et al, 2019;Qi et al, 2019;Magnusson and Dietz, 2019). In our experiments, we focused on neural architectures that considered all available contextual information within a sentence.…”
Section: Linguistic Features Previous Work On Toponym Detection In the Medical Domain Have Typically Taken Advantage Of Handcrafted Featumentioning
confidence: 99%