Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 2: Short Papers) 2017
DOI: 10.18653/v1/p17-2035
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: We present a neural architecture for containment relation identification between medical events and/or temporal expressions. We experiment on a corpus of deidentified clinical notes in English from the Mayo Clinic, namely the THYME corpus. Our model achieves an F-measure of 0.613 and outperforms the best result reported on this corpus to date.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
65
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 79 publications
(65 citation statements)
references
References 25 publications
0
65
0
Order By: Relevance
“…The recurrent neural network (RNN) architecture has been widely adopted by prior temporal extraction work to encode context information (Tourille et al, 2017;Cheng and Miyao, 2017;Meng et al, 2017). Motivated by these works, we adopt a RNN-based scoring function for both event and relation prediction in order to learn features in a data driven way and capture long-term contexts in the input.…”
Section: Multi-tasking Neural Scoring Functionmentioning
confidence: 99%
“…The recurrent neural network (RNN) architecture has been widely adopted by prior temporal extraction work to encode context information (Tourille et al, 2017;Cheng and Miyao, 2017;Meng et al, 2017). Motivated by these works, we adopt a RNN-based scoring function for both event and relation prediction in order to learn features in a data driven way and capture long-term contexts in the input.…”
Section: Multi-tasking Neural Scoring Functionmentioning
confidence: 99%
“…Analyzing the datasets which have numerical values, it's understood that the samples are continuous in nature. Hence Gaussian Naïve Bayesian network method (7) has been used for analyzing the prediction accuracies. Ontologies before integration are as shown in figures 5 and 6.…”
Section: Observations and Resultsmentioning
confidence: 99%
“…Prior to determining the effective measures towards treatment, the experts should have clear knowledge of symptoms and the related diseases [4]. Learning of the relationships between the various symptoms as attributes and the diseases as conclusions from the ontological representation can be done easily at entity level discovery with the use of triplet representation [5], discovery of diseases through the symptoms in the graphical path [6] and through the mining algorithms [7].…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Inspired by the SOTA approaches for the task (Tourille et al, 2017), we build a Bidirectional Long Short-Term Memory (BiLSTM) classifier (Hochreiter and Schmidhuber, 1997 concatenation of the last hidden states of both layers goes into the ouput layer. We train our network with the Adam (Kingma and Ba, 2014) optimization algorithm with a batch size of 64 and a learning rate of 0.001.…”
Section: Models For Temporal Relations Extractionmentioning
confidence: 99%