Copy the page URI to the clipboard
Samardzhiev, Krasen; Gargett, Andrew and Bollegala, Danushka
(2018).
URL: https://www.aclweb.org/anthology/S18-2004
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 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.
Viewing alternatives
Download history
Item Actions
Export
About
- Item ORO ID
- 73170
- Item Type
- Conference or Workshop Item
- Academic Unit or School
-
Faculty of Wellbeing, Education and Language Studies (WELS) > Languages and Applied Linguistics > Languages
Faculty of Wellbeing, Education and Language Studies (WELS) > Languages and Applied Linguistics
Faculty of Wellbeing, Education and Language Studies (WELS) - Copyright Holders
- © 2018 Association for Computational Linguistics
- Depositing User
- Andrew Gargett