Learning Neural Word Salience Scores

Samardzhiev, Krasen, Gargett, Andrew and Bollegala, Danushka (2017) Learning Neural Word Salience Scores. NAACL HLT 2018 - Lexical and Computational Semantics, SEM 2018, Proceedings of the 7th Conference, abs/17. pp. 33-42.

Text 1709.01186v1.pdf - Author Accepted Manuscript Download (421kB)

Abstract

Measuring the salience of a word is an essential step in numerous NLP tasks. Heuristic approaches such as tfidf have been used so far to estimate the salience of words. We propose \emph{Neural Word Salience} (NWS) scores, unlike heuristics, are learnt from a corpus. Specifically, we learn word salience scores such that, using pre-trained word embeddings as the input, can accurately predict the words that appear in a sentence, given the words that appear in the sentences preceding or succeeding that sentence. Experimental results on sentence similarity prediction show that the learnt word salience scores perform comparably or better than some of the state-of-the-art approaches for representing sentences on benchmark datasets for sentence similarity, while using only a fraction of the training and prediction times required by prior methods. Moreover, our NWS scores positively correlate with psycholinguistic measures such as concreteness, and imageability implying a close connection to the salience as perceived by humans.

Item Type:	Article
Uncontrolled Keywords:	cs.CL, cs.CL
Depositing User:	Symplectic Admin
Date Deposited:	11 Sep 2017 09:48
Last Modified:	19 Jan 2023 06:55
Related URLs:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3009361