Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783131256> ?p ?o ?g. }
- W2783131256 abstract "Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Keyphrases can be used for indexing, searching, aggregating and summarizing text documents, serving many automatic as well as human-facing use cases. Existing supervised systems for keyphrase extraction require large amounts of labeled training data and generalize very poorly outside the domain of the training data. At the same time, unsupervised systems found in the literature have poor accuracy, and often do not generalize well, as they require the input document to belong to a larger corpus also given as input. Furthermore, both supervised and unsupervised methods are often too slow for real-time scenarios and suffer from over-generation. Addressing these drawbacks, in this paper, we introduce an unsupervised method for keyphrase extraction from single documents that leverages sentence embeddings. By selecting phrases whose semantic embeddings are close to the embeddings of the whole document, we are able to separate the best candidate phrases from the rest. We show that our embedding-based method is not only simpler, but also more effective than graph-based state of the art systems, achieving higher F-scores on standard datasets. Simplicity is a significant advantage, especially when processing large amounts of documents from the Web, resulting in considerable speed gains. Moreover, we describe how to increase coverage and diversity among the selected keyphrases by introducing an embedding-based maximal marginal relevance (MMR) for new phrases. A user study including over 200 votes showed that, although reducing the phrase semantic overlap leads to no gains in terms of F-score, our diversity enriched selection is preferred by humans." @default.
- W2783131256 created "2018-01-26" @default.
- W2783131256 creator A5010309406 @default.
- W2783131256 creator A5011328096 @default.
- W2783131256 creator A5012134536 @default.
- W2783131256 creator A5022269155 @default.
- W2783131256 creator A5073756389 @default.
- W2783131256 date "2018-01-13" @default.
- W2783131256 modified "2023-09-27" @default.
- W2783131256 title "EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings." @default.
- W2783131256 cites W1490343430 @default.
- W2783131256 cites W1525595230 @default.
- W2783131256 cites W1854214752 @default.
- W2783131256 cites W1949395974 @default.
- W2783131256 cites W1993320088 @default.
- W2783131256 cites W2045181608 @default.
- W2783131256 cites W2064418625 @default.
- W2783131256 cites W2083305840 @default.
- W2783131256 cites W2160517426 @default.
- W2783131256 cites W2167329753 @default.
- W2783131256 cites W2250539671 @default.
- W2783131256 cites W2251295945 @default.
- W2783131256 cites W2493916176 @default.
- W2783131256 cites W2604853468 @default.
- W2783131256 cites W2950577311 @default.
- W2783131256 cites W2950726992 @default.
- W2783131256 cites W2963245897 @default.
- W2783131256 cites W2963514026 @default.
- W2783131256 cites W32253530 @default.
- W2783131256 hasPublicationYear "2018" @default.
- W2783131256 type Work @default.
- W2783131256 sameAs 2783131256 @default.
- W2783131256 citedByCount "4" @default.
- W2783131256 countsByYear W27831312562020 @default.
- W2783131256 countsByYear W27831312562021 @default.
- W2783131256 countsByYear W27831312562022 @default.
- W2783131256 crossrefType "posted-content" @default.
- W2783131256 hasAuthorship W2783131256A5010309406 @default.
- W2783131256 hasAuthorship W2783131256A5011328096 @default.
- W2783131256 hasAuthorship W2783131256A5012134536 @default.
- W2783131256 hasAuthorship W2783131256A5022269155 @default.
- W2783131256 hasAuthorship W2783131256A5073756389 @default.
- W2783131256 hasConcept C132525143 @default.
- W2783131256 hasConcept C154945302 @default.
- W2783131256 hasConcept C158154518 @default.
- W2783131256 hasConcept C162324750 @default.
- W2783131256 hasConcept C177264268 @default.
- W2783131256 hasConcept C17744445 @default.
- W2783131256 hasConcept C187736073 @default.
- W2783131256 hasConcept C199360897 @default.
- W2783131256 hasConcept C199539241 @default.
- W2783131256 hasConcept C204321447 @default.
- W2783131256 hasConcept C23123220 @default.
- W2783131256 hasConcept C2777530160 @default.
- W2783131256 hasConcept C2780288562 @default.
- W2783131256 hasConcept C2780451532 @default.
- W2783131256 hasConcept C41008148 @default.
- W2783131256 hasConcept C41608201 @default.
- W2783131256 hasConcept C75165309 @default.
- W2783131256 hasConcept C80444323 @default.
- W2783131256 hasConceptScore W2783131256C132525143 @default.
- W2783131256 hasConceptScore W2783131256C154945302 @default.
- W2783131256 hasConceptScore W2783131256C158154518 @default.
- W2783131256 hasConceptScore W2783131256C162324750 @default.
- W2783131256 hasConceptScore W2783131256C177264268 @default.
- W2783131256 hasConceptScore W2783131256C17744445 @default.
- W2783131256 hasConceptScore W2783131256C187736073 @default.
- W2783131256 hasConceptScore W2783131256C199360897 @default.
- W2783131256 hasConceptScore W2783131256C199539241 @default.
- W2783131256 hasConceptScore W2783131256C204321447 @default.
- W2783131256 hasConceptScore W2783131256C23123220 @default.
- W2783131256 hasConceptScore W2783131256C2777530160 @default.
- W2783131256 hasConceptScore W2783131256C2780288562 @default.
- W2783131256 hasConceptScore W2783131256C2780451532 @default.
- W2783131256 hasConceptScore W2783131256C41008148 @default.
- W2783131256 hasConceptScore W2783131256C41608201 @default.
- W2783131256 hasConceptScore W2783131256C75165309 @default.
- W2783131256 hasConceptScore W2783131256C80444323 @default.
- W2783131256 hasLocation W27831312561 @default.
- W2783131256 hasOpenAccess W2783131256 @default.
- W2783131256 hasPrimaryLocation W27831312561 @default.
- W2783131256 hasRelatedWork W1525595230 @default.
- W2783131256 hasRelatedWork W2064418625 @default.
- W2783131256 hasRelatedWork W2251295945 @default.
- W2783131256 hasRelatedWork W2740811004 @default.
- W2783131256 hasRelatedWork W2752172973 @default.
- W2783131256 hasRelatedWork W2763948453 @default.
- W2783131256 hasRelatedWork W2825128598 @default.
- W2783131256 hasRelatedWork W2888766462 @default.
- W2783131256 hasRelatedWork W2926825864 @default.
- W2783131256 hasRelatedWork W2951795926 @default.
- W2783131256 hasRelatedWork W2952494277 @default.
- W2783131256 hasRelatedWork W2952531073 @default.
- W2783131256 hasRelatedWork W2989576008 @default.
- W2783131256 hasRelatedWork W3025782987 @default.
- W2783131256 hasRelatedWork W3045913839 @default.
- W2783131256 hasRelatedWork W3089244638 @default.
- W2783131256 hasRelatedWork W3090635823 @default.
- W2783131256 hasRelatedWork W3100652389 @default.
- W2783131256 hasRelatedWork W3156988118 @default.