Learning Neural Word Salience Scores

Samardzhiev, Krasen; Gargett, Andrew and Bollegala, Danushka (2018). Learning Neural Word Salience Scores. In: Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, 5-6 Jun 2018, New Orleans, LA, USA, Association for Computational Linguistics, pp. 33–42.

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 \textitNeural 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

Recommendations