Title-Guided Encoding for Keyphrase Generation
Other conference paper

Full Text

Times Cited
Web of Science3WOS source URL (as at 20/09/2021) Click here for the latest count

Other information
AbstractKeyphrase generation (KG) aims to generate a set of keyphrases given a document, which is a fundamental task in natural language processing (NLP). Most previous methods solve this problem in an extractive manner, while recently, several attempts are made under the generative setting using deep neural networks. However, the state-of-the-art generative methods simply treat the document title and the document main body equally, ignoring the leading role of the title to the overall document. To solve this problem, we introduce a new model called Title-Guided Network (TG-Net) for automatic keyphrase generation task based on the encoder-decoder architecture with two new features: (i) the title is additionally employed as a query-like input, and (ii) a title-guided encoder gathers the relevant information from the title to each word in the document. Experiments on a range of KG datasets demonstrate that our model outperforms the state-of-the-art models with a large margin, especially for documents with either very low or very high title length ratios.
Acceptance Date01/11/2018
All Author(s) ListChen Wang, Gao Yifan, Zhang Jiani, King Irwin, Lyu Michael
Name of ConferenceAAAI-19: Thirty-Third AAAI conference on Artificial Intelligence
Start Date of Conference27/01/2019
End Date of Conference01/02/2019
Place of ConferenceHonolulu, Hawaii, USA
Country/Region of ConferenceUnited States of America
Proceedings Title33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence
Book titleAAAI2019
Pages6268 - 6275
LanguagesEnglish-United States
KeywordsKeyphrase Generation, Generation, Natural Language Processing

Last updated on 2021-21-09 at 00:41