UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings

Add code
May 25, 2018
Arshia Z. Hassan, Manikya S. Vallabhajosyula, Ted Pedersen
Figure 1 for UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings
Figure 2 for UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings
Figure 3 for UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings
Figure 4 for UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

Hypernym Discovery is the task of identifying potential hypernyms for a given term. A hypernym is a more generalized word that is super-ordinate to more specific words. This paper explores several approaches that rely on co-occurrence frequencies of word pairs, Hearst Patterns based on regular expressions, and word embeddings created from the UMBC corpus. Our system Babbage participated in Subtask 1A for English and placed 6th of 19 systems when identifying concept hypernyms, and 12th of 18 systems for entity hypernyms.

* 5 pages, to Appear in the Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval 2018), June 2018, New Orleans, LA  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon