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

Arshia Z. Hassan, Manikya S. Vallabhajosyula, Ted Pedersen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

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.

Original languageEnglish (US)
Title of host publicationNAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop
EditorsMarianna Apidianaki, Marianna Apidianaki, Saif M. Mohammad, Jonathan May, Ekaterina Shutova, Steven Bethard, Marine Carpuat
PublisherAssociation for Computational Linguistics (ACL)
Pages914-918
Number of pages5
ISBN (Electronic)9781948087209
StatePublished - 2018
Event12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the - New Orleans, United States
Duration: Jun 5 2018Jun 6 2018

Publication series

NameNAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop

Conference

Conference12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the
Country/TerritoryUnited States
CityNew Orleans
Period6/5/186/6/18

Bibliographical note

Funding Information:
This project was carried out as a part of CS 8761, Natural Language Processing, a graduate level class offered in Fall 2017 at the University of Minnesota, Duluth by Dr. Ted Pedersen. All authors of this paper have contributed equally and are listed in alphabetical order by first name.

Publisher Copyright:
© 2018 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings'. Together they form a unique fingerprint.

Cite this