Research Area:  Machine Learning

Abstract:

We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies on large amounts of labeled data, which is only applicable to resource-rich domains. In this paper, we propose semi-supervised keyphrase generation methods by leveraging both labeled data and large-scale unlabeled samples for learning. Two strategies are proposed. First, unlabeled documents are first tagged with synthetic keyphrases obtained from unsupervised keyphrase extraction methods or a selflearning algorithm, and then combined with labeled samples for training. Furthermore, we investigate a multi-task learning framework to jointly learn to generate keyphrases as well as the titles of the articles. Experimental results show that our semi-supervised learning-based methods outperform a state-of-the-art model trained with labeled data only.

Keywords:  
Semi-Supervised Learning
Neural Keyphrase Generation
sequence-to-sequence (seq2seq) models
keyphrase extraction
Machine Learning
Deep Learning

Author(s) Name:  Hai Ye, Lu Wang

Publisher name:  arXiv:1808.06773

DOI:  10.48550/arXiv.1808.06773

Volume Information:  

Paper Link:   https://arxiv.org/abs/1808.06773