458 Hits in 4.5 sec

Automatic Construction and Ranking of Topical Keyphrases on Collections of Short Documents [chapter]

Marina Danilevsky, Chi Wang, Nihit Desai, Xiang Ren, Jingyi Guo, Jiawei Han
2014 Proceedings of the 2014 SIAM International Conference on Data Mining  
We introduce a framework for topical keyphrase generation and ranking, based on the output of a topic model run on a collection of short documents.  ...  We study the performance of our framework on multiple real world document collections, and also show that it is more scalable than comparable phrase-generating models.  ...  DBLP Conclusion In this work we introduce a framework for topical keyphrase generation and ranking, building on the output of a topic model run on a collection of short documents.  ... 
doi:10.1137/1.9781611973440.46 dblp:conf/sdm/DanilevskyWDRGH14 fatcat:7atsnm7ywve7diraiuwj562jra

KERT: Automatic Extraction and Ranking of Topical Keyphrases from Content-Representative Document Titles [article]

Marina Danilevsky, Chi Wang, Nihit Desai, Jingyi Guo, Jiawei Han
2013 arXiv   pre-print
We introduce KERT (Keyphrase Extraction and Ranking by Topic), a framework for topical keyphrase generation and ranking.  ...  The effectiveness of our approach is demonstrated on two collections of content-representative titles in the domains of Computer Science and Physics.  ...  TextRank (Mihalcea and Tarau, 2004) constructs keyphrases from the top ranked unigrams in a document collection.  ... 
arXiv:1306.0271v1 fatcat:w6iib3arkjbvjpbbnama73ovxy

Automatic keyphrase extraction using graph-based methods

Josiane Mothe, Faneva Ramiandrisoa, Michael Rasolomanana
2018 Proceedings of the 33rd Annual ACM Symposium on Applied Computing - SAC '18  
This paper analyses various unsupervised automatic keyphrase extraction methods based on graphs as well as the impact of word embedding. Evaluation is made on three datasets.  ...  We show that there is no differences when using word embedding and when not using it.  ...  Candidate keyphrases construction and ranking: candidate keyphrases are sequences of adjacent words in documents restricted to nouns and adjectives only.  ... 
doi:10.1145/3167132.3167392 dblp:conf/sac/MotheRR18 fatcat:gdzgl2rdu5eh5ob5gc2uak5h2u

Topic-based browsing within a digital library using keyphrases

Steve Jones, Gordon Paynter
1999 Proceedings of the fourth ACM conference on Digital libraries - DL '99  
Automatic keyphrase extraction is exploited to identify link anchors, and keyphraseÐbased similarity measures are used to select and rank destinations.  ...  Two implementations are described: one that applies these techniques to existing WWWÐbased digital library collections using standard HTML, and one that uses a wider range of interface techniques to provide  ...  Many thanks also to Carl Gutwin for implementation of the first Phrasier prototype, and producing the keyphrase indexes originally used by Phrasier.  ... 
doi:10.1145/313238.313279 dblp:conf/dl/JonesP99 fatcat:kl45z4c62vay5nosstd2rkknje

Topical Keyphrase Extraction with Hierarchical Semantic Networks [article]

Yoo yeon Sung, Seoung Bum Kim
2019 arXiv   pre-print
Topical keyphrase extraction is used to summarize large collections of text documents.  ...  We conduct experiments on real data to examine the practicality of the proposed method and to compare its performance with that of existing topical keyphrase extraction methods.  ...  Acknowledgements The authors would like to thank the editor and reviewers for their useful comments and suggestions, which were greatly help in improving the quality of the paper.  ... 
arXiv:1910.07848v1 fatcat:4jaubp7uwbhlve24zxll5oezwq

Improving browsing in digital libraries with keyphrase indexes

Carl Gutwin, Gordon Paynter, Ian Witten, Craig Nevill-Manning, Eibe Frank
1999 Decision Support Systems  
Automatically-extracted keyphrases form the basic unit of both indexing and presentation, allowing users to interact with the collection at the level of topics and subjects rather than words and documents  ...  Conventional systems often operate at the wrong level, indexing words when people think in terms of topics, and returning documents when people want a broader view.  ...  Kea, the system used to extract keyphrases for Keyphind, is available from  ... 
doi:10.1016/s0167-9236(99)00038-x fatcat:kb6ixweypfa2dgtdhtyhhvll6u

Learning Feature Representations for Keyphrase Extraction [article]

Corina Florescu, Wei Jin
2018 arXiv   pre-print
Our model represents the document as a graph and automatically learns feature representation of phrases. The proposed model obtains remarkable improvements in performance over strong baselines.  ...  In supervised approaches for keyphrase extraction, a candidate phrase is encoded with a set of hand-crafted features and machine learning algorithms are trained to discriminate keyphrases from non-keyphrases  ...  Introduction Keyphrase extraction (KE) is the task of automatically extracting descriptive phrases or concepts that represent the main topics of a document.  ... 
arXiv:1801.01768v1 fatcat:jde2cxpgr5fivd27tsqatdbkni

WikiRank: Improving Keyphrase Extraction Based on Background Knowledge [article]

Yang Yu, Vincent Ng
2018 arXiv   pre-print
Keyphrase is an efficient representation of the main idea of documents.  ...  In this paper, we propose WikiRank, an unsupervised method for keyphrase extraction based on the background knowledge from Wikipedia. Firstly, we construct a semantic graph for the document.  ...  Automatic keyphrase extraction concerns "the automatic selection of important and topical phrases from the body of a document".  ... 
arXiv:1803.09000v1 fatcat:jhxjphn4dncafdlrnn44yga2hq

Creation and evaluation of large keyphrase extraction collections with multiple opinions

Lucas Sterckx, Thomas Demeester, Johannes Deleu, Chris Develder
2017 Language Resources and Evaluation  
A first systematic evaluation of ranking and classification of keyphrases using both unsupervised and supervised AKE techniques on the test collections shows a superior effectiveness of supervised models  ...  While several Automatic Keyphrase Extraction (AKE) techniques have been developed and analyzed, there is little consensus on the definition of the task and a lack of overview of the effectiveness of different  ...  known as Flanders Innovation & Entrepreneurship) and Innoviris.  ... 
doi:10.1007/s10579-017-9395-6 fatcat:4ylkgeswhzaevof2rbtdcy2d3i

Keyphrase Extraction Using Deep Recurrent Neural Networks on Twitter

Qi Zhang, Yang Wang, Yeyun Gong, Xuanjing Huang
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
Different from previous studies, which are usually focused on automatically extracting keyphrases from documents or articles, in this study, we considered the problem of automatically extracting keyphrases  ...  To evaluate the proposed method, we also constructed a large-scale dataset collected from Twitter.  ...  This work was partially funded by National Natural Science Foundation of China (No. 61532011, 61473092, and 61472088) , the National High Technology Research and Development Program of China (No. 2015AA015408  ... 
doi:10.18653/v1/d16-1080 dblp:conf/emnlp/ZhangWGH16 fatcat:na2oqckrtndg5ka3aj5jqif4na

Constructing Topic-specific Search Keyphrase Suggestion Tools for Web Information Retrieval

Pirkola Ari
2020 Zenodo  
The keyphrases are identified and out-oftopic phrases removed based on their frequencies in the text corpora of various densities of text discussing the topic.  ...  We devised a method to extract keyphrases from the Web pages to construct a keyphrase list for a specific topic.  ...  Acknowledgments This study was funded by the Academy of Finland (research projects 130760, 218289).  ... 
doi:10.5281/zenodo.4134558 fatcat:q3xd6dcvbbbofft4se2f7mrpci

Automatic Keyphrase Extraction: A Survey of the State of the Art

Kazi Saidul Hasan, Vincent Ng
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We present a survey of the state of the art in automatic keyphrase extraction, examining the major sources of errors made by existing systems and discussing the challenges ahead.  ...  While automatic keyphrase extraction has been examined extensively, state-of-theart performance on this task is still much lower than that on many core natural language processing tasks.  ...  Acknowledgments We thank the anonymous reviewers for their detailed and insightful comments on earlier drafts of this paper. This work was supported in part by NSF Grants IIS-1147644 and IIS-1219142.  ... 
doi:10.3115/v1/p14-1119 dblp:conf/acl/HasanN14 fatcat:btbm5chndbgwhkisa7dzgyilwy

Supervised Keyphrase Extraction as Positive Unlabeled Learning

Lucas Sterckx, Cornelia Caragea, Thomas Demeester, Chris Develder
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
We show that performance of trained keyphrase extractors approximates a classifier trained on articles labeled by multiple annotators, leading to higher average F 1 scores and better rankings of keyphrases  ...  The problem of noisy and unbalanced training data for supervised keyphrase extraction results from the subjectivity of keyphrase assignment, which we quantify by crowdsourcing keyphrases for news and fashion  ...  The research presented in this article relates to STEAMER ( 2014/07/12/steamer), a MiX-ICON project facilitated by iMinds Media and funded by IWT and Innoviris.  ... 
doi:10.18653/v1/d16-1198 dblp:conf/emnlp/SterckxCDD16 fatcat:gksar6rgd5etppvskydppaxg5a

Bringing Order to Digital Libraries: From Keyphrase Extraction to Index Term Assignment

Nicolai Erbs, Iryna Gurevych, Marc Rittberger
2013 D-Lib Magazine  
We observe a different ranking of approaches depending on the evaluation metric. Precision and recall are based on the best 10 extracted keyphrases.  ...  Newman states that assigning index terms requires knowledge of the whole document collection, while keyphrases are assigned based on a single document.  ... 
doi:10.1045/september2013-erbs fatcat:hm2lmbajmzfxhdnebu64del3he

Creating a Testbed for the Evaluation of Automatically Generated Back-of-the-Book Indexes [chapter]

Andras Csomai, Rada F. Mihalcea
2006 Lecture Notes in Computer Science  
correspondence that can be established between techniques for automatic index construction and keyphrase extraction.  ...  Finally, we investigate the properties of the gold standard index, such as index size, length of index entries, and upper bounds on coverage as indicated by the presence of index entries in the document  ...  The method is intended to extract keyphrases not from a single document, but from a collection of documents.  ... 
doi:10.1007/11671299_45 fatcat:xgobvjxrhnazxghcfltaaldz2i
« Previous Showing results 1 — 15 out of 458 results