Abstract | ||
---|---|---|
Automatic Keyphrase Extraction describes the process of extracting keywords or keyphrases from the body of a document. To our knowledge until now all algorithms rely on a set of manually crafted statistical features to model word importance. In this paper we propose an end-to-end neural keyphrase extraction algorithm using a siamese LSTM network, eliminating the need for manual feature engineering. We train and evaluate our model on the Inspec [6] dataset for keyphrase extraction and achieve comparable results to state-of-the-art algorithms. |
Year | Venue | Field |
---|---|---|
2018 | MLDM | Inspec,Pattern recognition,Computer science,Extraction algorithm,Keyword extraction,Recurrent neural network,Feature engineering,Artificial intelligence,Artificial neural network,Machine learning |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
11 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Johannes Villmow | 1 | 0 | 0.34 |
Marco Wrzalik | 2 | 0 | 1.35 |
Dirk Krechel | 3 | 44 | 13.19 |