Learning Neural Word Salience Scores
This addresses the need for efficient and accurate word salience estimation in NLP tasks, offering an incremental improvement over heuristic approaches like tfidf.
The paper tackles the problem of measuring word salience in NLP by proposing Neural Word Salience (NWS) scores, which are learned from a corpus using pre-trained word embeddings to predict words in sentences based on context, resulting in performance comparable or better than state-of-the-art methods on sentence similarity benchmarks with significantly reduced training and prediction times.
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.