Thumbnail Image
Item

Wolves at SemEval-2018 task 10: Semantic discrimination based on knowledge and association

Taslimipoor, Shiva
; 
Rohanian, Omid
; 
Ha, Le An
; 
Corpas Pastor, Gloria
; 
Mitkov, Ruslan
Authors
Taslimipoor, Shiva
 Rohanian, Omid
 Ha, Le An
 Corpas Pastor, Gloria
 Mitkov, Ruslan
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2018-06
Submitted date
Subjects
Semantics
 knowledge-base
 co-occurrence
 Conceptnet
Show all metadata
Files
Thumbnail Image
semeval_task10.pdf
Adobe PDF, 121.24 KB
Alternative
Abstract
This paper describes the system submitted to SemEval 2018 shared task 10 ‘Capturing Discriminative Attributes’. We use a combination of knowledge-based and co-occurrence features to capture the semantic difference between two words in relation to an attribute. We define scores based on association measures, ngram counts, word similarity, and ConceptNet relations. The system is ranked 4th (joint) on the official leaderboard of the task.
Citation
Publisher
Association for Computational Linguistics
Journal
International Workshop on Semantic Evaluation
Research Unit
URI
http://hdl.handle.net/2436/621757
DOI
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
Type
Conference contribution
Language
en
Description
Series/Report no.
ISSN
EISSN
ISBN
9781948087209
ISMN
Gov't Doc #
Sponsors
Research Group in Computational Linguistics
Rights
Research Projects
Organizational Units
Journal Issue
Embedded videos
Collections
Research Institute in Information and Language Processing