eprintid: 1550
rev_number: 9
eprint_status: archive
userid: 243
dir: disk0/00/00/15/50
datestamp: 2016-05-23 03:00:03
lastmod: 2016-05-23 03:01:00
status_changed: 2016-05-23 03:00:03
type: conference_item
metadata_visibility: show
creators_name: Tran, Mai Vu
creators_name: Le, Hoang Quynh
creators_name: Phi, Van Thuy
creators_name: Pham, Thanh Binh
creators_name: Nigel, Collier
creators_id: vutm@vnu.edu.vn
title: Exploring a Probabilistic Earley Parser for Event Composition in Biomedical Texts
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: We describe a high precision system for extracting events of biomedical significance that was developed during the BioNLP shared task 2013 and tested on the Cancer Genetics data set. Our system explored a multi-stage approach including trigger detection, edge detection and event composition. After trigger edge detection is finished we are left with a semantic graph from which we must select the optimal subset that is consistent with the semantic frames for each event type.  The system achieved an F-score on the development data of 73.67 but was ranked 5th out of six with an F-score of 29.94 on the test data. How-ever, precision was the second highest ranked on the task at 62.73. Analysis suggests the need to continue to improve our system for complex events particularly taking into account cross-domain differences in argument distributions.
date: 2016-03-26
date_type: published
full_text_status: public
pres_type: poster
event_title: SW4PHD: the 2016 Scientific Workshop for PhD Students
event_location: Hanoi
event_dates: 26 March 2016
event_type: workshop
refereed: TRUE
citation:   Tran, Mai Vu and Le, Hoang Quynh and Phi, Van Thuy and Pham, Thanh Binh and Nigel, Collier  (2016) Exploring a Probabilistic Earley Parser for Event Composition in Biomedical Texts.  In: SW4PHD: the 2016 Scientific Workshop for PhD Students, 26 March 2016, Hanoi.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/1550/1/BIONLP2013_poster%20v1.0.pdf