Learning Neural Word Salience Scores

TL;DR

This paper introduces Neural Word Salience scores learned from data, which improve sentence similarity tasks and align with human perception measures, offering a more efficient alternative to heuristic methods.

Contribution

The paper presents a neural approach to learn word salience scores from corpora, outperforming heuristics like tfidf in sentence similarity tasks and correlating with psycholinguistic measures.

Findings

NWS scores perform comparably or better than state-of-the-art methods.

NWS scores require less training and prediction time.

NWS scores correlate with human perceptual measures.

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.