Acquiring Lexical Semantic Knowledge
Department of Computer Science
Bar-Ilan University
AS6 Level 5
MR6, AS6-05-10
Abstract:
Recognizing lexical semantic relations between words is an essential component in semantic applications. In question answering, for instance, answering the question "When did Google buy YouTube?" given the text "Google acquired YouTube on November 13, 2006" requires identifying that 'buy' and 'acquire' are synonymous in this context. Semantic relations such as synonymy (tall, high) and hypernymy (cat, pet) are used to infer the meaning of one word from another, in order to overcome lexical variability.
In this talk, I will present two methods for automatic acquisition of lexical semantic knowledge from text: the first is a neural method for recognizing semantic relations between nouns (e.g. part_of: (tail, cat)), and the second is an unsupervised method for extracting predicate paraphrases (e.g X buy Y -- X acquire Y) from news headlines in Twitter.
Biodata:
Vered Shwartz is a Computer Science PhD student in Natural Language Processing lab at Bar-Ilan University, under the supervision of Prof. Ido Dagan. Her research focuses on recognizing lexical semantic relations between words. Her recent work involved an integrated distributional and path-based method for recognizing semantic relations, and an automatically-constructed resource of predicate paraphrases. She completed her B.Sc. (2013) and M.Sc. (2015) in Computer Science in Bar-Ilan University.