SGG: Learning to Select, Guide, and Generate for Keyphrase Generation

TL;DR

The paper introduces SGG, a hierarchical neural network that separately handles present and absent keyphrase generation, significantly improving performance on benchmark datasets and extending to title generation tasks.

Contribution

SGG is a novel hierarchical model that explicitly distinguishes and separately generates present and absent keyphrases, advancing keyphrase generation methods.

Findings

SGG outperforms strong baselines on four keyphrase benchmarks.

The model effectively generates both present and absent keyphrases.

SGG can be extended to other natural language generation tasks like title creation.

Abstract

Keyphrases, that concisely summarize the high-level topics discussed in a document, can be categorized into present keyphrase which explicitly appears in the source text, and absent keyphrase which does not match any contiguous subsequence but is highly semantically related to the source. Most existing keyphrase generation approaches synchronously generate present and absent keyphrases without explicitly distinguishing these two categories. In this paper, a Select-Guide-Generate (SGG) approach is proposed to deal with present and absent keyphrase generation separately with different mechanisms. Specifically, SGG is a hierarchical neural network which consists of a pointing-based selector at low layer concentrated on present keyphrase generation, a selection-guided generator at high layer dedicated to absent keyphrase generation, and a guider in the middle to transfer information from selector to generator. Experimental results on four keyphrase generation benchmarks demonstrate the effectiveness of our model, which significantly outperforms the strong baselines for both present and absent keyphrases generation. Furthermore, we extend SGG to a title generation task which indicates its extensibility in natural language generation tasks.