Cross-Domain Keyword Extraction with Keyness Patterns

TL;DR

This paper introduces a supervised neural network approach for keyword extraction that leverages community-level keyness patterns, demonstrating state-of-the-art results and robustness across multiple domains.

Contribution

It proposes a novel supervised ranking method using convolutional neural networks to learn keyness patterns, addressing domain dependence and annotation subjectivity in keyword extraction.

Findings

Achieves an average top-10-F-measure of 0.316 on ten datasets

Demonstrates robust cross-domain performance with 0.346 F-measure

Outperforms existing methods in supervised keyword extraction

Abstract

Domain dependence and annotation subjectivity pose challenges for supervised keyword extraction. Based on the premises that second-order keyness patterns are existent at the community level and learnable from annotated keyword extraction datasets, this paper proposes a supervised ranking approach to keyword extraction that ranks keywords with keyness patterns consisting of independent features (such as sublanguage domain and term length) and three categories of dependent features -- heuristic features, specificity features, and representavity features. The approach uses two convolutional-neural-network based models to learn keyness patterns from keyword datasets and overcomes annotation subjectivity by training the two models with bootstrap sampling strategy. Experiments demonstrate that the approach not only achieves state-of-the-art performance on ten keyword datasets in general supervised keyword extraction with an average top-10-F-measure of 0.316 , but also robust cross-domain performance with an average top-10-F-measure of 0.346 on four datasets that are excluded in the training process. Such cross-domain robustness is attributed to the fact that community-level keyness patterns are limited in number and temperately independent of language domains, the distinction between independent features and dependent features, and the sampling training strategy that balances excess risk and lack of negative training data.