English

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

Computation and Language 2021-10-14 v2 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2105.02544,
  title  = {SGG: Learning to Select, Guide, and Generate for Keyphrase Generation},
  author = {Jing Zhao and Junwei Bao and Yifan Wang and Youzheng Wu and Xiaodong He and Bowen Zhou},
  journal= {arXiv preprint arXiv:2105.02544},
  year   = {2021}
}

Comments

10 pages, 4 figures, accepted by NAACL2021

R2 v1 2026-06-24T01:49:56.327Z