Unsupervised Keyphrase Extraction via Interpretable Neural Networks

TL;DR

This paper introduces INSPECT, an unsupervised method using self-explaining neural networks to identify influential keyphrases for document classification, outperforming previous heuristic-based approaches.

Contribution

The paper presents a novel, interpretable neural network approach for unsupervised keyphrase extraction that eliminates the need for heuristic importance measures.

Findings

Achieves state-of-the-art results across four datasets

Effectively identifies influential keyphrases for topic prediction

Reduces reliance on domain-specific heuristics

Abstract

Keyphrase extraction aims at automatically extracting a list of "important" phrases representing the key concepts in a document. Prior approaches for unsupervised keyphrase extraction resorted to heuristic notions of phrase importance via embedding clustering or graph centrality, requiring extensive domain expertise. Our work presents a simple alternative approach which defines keyphrases as document phrases that are salient for predicting the topic of the document. To this end, we propose INSPECT -- an approach that uses self-explaining models for identifying influential keyphrases in a document by measuring the predictive impact of input phrases on the downstream task of the document topic classification. We show that this novel method not only alleviates the need for ad-hoc heuristics but also achieves state-of-the-art results in unsupervised keyphrase extraction in four datasets across two domains: scientific publications and news articles.