Meerkat Mafia: Multilingual and Cross-Level Semantic Textual Similarity systems
Links to Files
https://ebiquity.umbc.edu/paper/html/id/659/Meerkat-Mafia-Multilingual-and-Cross-Level-Semantic-Textual-Similarity-systemsPermanent Link
http://hdl.handle.net/11603/11834Collections
Metadata
Show full item recordDate
2014-08-23Type of Work
8 pagesText
conference papers and proceedings pre-print and slides
Citation of Original Publication
Abhay Kashyap, Lushan Han, Roberto Yus, Jennifer Sleeman, Taneeya Satyapanich, Sunil Gandhi and Tim Finin, Meerkat Mafia: Multilingual and Cross-Level Semantic Textual Similarity Systems, Int. Workshop on Semantic Evaluation, Association for Computational Linguistics, August 2014, https://ebiquity.umbc.edu/paper/html/id/659/Meerkat-Mafia-Multilingual-and-Cross-Level-Semantic-Textual-Similarity-systemsRights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.Subjects
human language technologylexical semantics
natural language processing
semantics
UMBC Ebiquity Research Group
Abstract
We describe UMBC's systems developed for the SemEval 2014 tasks on Multilingual Semantic Textual Similarity (Task 10) and Cross-Level Semantic Similarity (Task 3). Our best submission in the Multilingual task ranked second in both English and Spanish subtasks using an unsupervised approach. Our best systems for Cross-Level task ranked second in Paragraph-Sentence and first in both Sentence-Phrase and Word-Sense subtask. The system ranked first for the Phrase- Word subtask but was not included in the official results due to a late submission.