{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:50:28Z","timestamp":1743105028778,"version":"3.40.3"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319254845"},{"type":"electronic","value":"9783319254852"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-25485-2_1","type":"book-chapter","created":{"date-parts":[[2015,12,9]],"date-time":"2015-12-09T15:29:25Z","timestamp":1449674965000},"page":"3-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Document Analysis and Retrieval Tasks in Scientific Digital Libraries"],"prefix":"10.1007","author":[{"given":"Sujatha Das","family":"Gollapalli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelia","family":"Caragea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. Lee","family":"Giles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,10]]},"reference":[{"issue":"2","key":"1_CR1","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1023\/A:1017919924342","volume":"52","author":"WW Hood","year":"2001","unstructured":"Hood, W.W., Wilson, C.S.: The literature of bibliometrics, scientometrics, and informetrics. Scientometrics 52(2), 291\u2013314 (2001)","journal-title":"Scientometrics"},{"key":"1_CR2","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR3","unstructured":"Boudin, F.: A comparison of centrality measures for graph-based keyphrase extraction. In: IJCNLP (2013)"},{"issue":"2","key":"1_CR4","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1023\/A:1009715923555","volume":"2","author":"CJC Burges","year":"1998","unstructured":"Burges, C.J.C.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2(2), 121\u2013167 (1998)","journal-title":"Data Min. Knowl. Discov."},{"key":"1_CR5","unstructured":"Caragea, C., Wu, J., Williams, K., Gollapalli, S.D., Khabsa, M., Teregowda, P., Giles, C.L.: Automatic identification of research articles from crawled documents. In: Web-Scale Classification: Classifying Big Data from the Web, Co-Located with WSDM (2014)"},{"key":"1_CR6","volume-title":"Mining the Web: Discovering Knowledge from Hypertext Data","author":"S Chakrabarti","year":"2002","unstructured":"Chakrabarti, S.: Mining the Web: Discovering Knowledge from Hypertext Data. Morgan-Kauffman, Burlington (2002)"},{"issue":"11\u201316","key":"1_CR7","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1016\/S1389-1286(99)00052-3","volume":"31","author":"S Chakrabarti","year":"1999","unstructured":"Chakrabarti, S., van den Berg, M., Dom, B.: Focused crawling: a new approach to topic-specific web resource discovery. Comput. Netw. 31(11\u201316), 1623\u20131640 (1999)","journal-title":"Comput. Netw."},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Chen, B., Zhu, L., Kifer, D., Lee, D.: What is an opinion about? exploring political standpoints using opinion scoring model. In: AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7717"},{"key":"1_CR9","unstructured":"Councill, I.G., Giles, C.L., Kan, M.-Y.: Parscit: an open-source crf reference string parsing package. In: LREC (2008)"},{"issue":"6","key":"1_CR10","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"SC Deerwester","year":"1990","unstructured":"Deerwester, S.C., Dumais, S.T., Landauer, T.K., Furnas, G.W., Harshman, R.A.: Indexing by latent semantic analysis. JASIS 41(6), 391\u2013407 (1990)","journal-title":"JASIS"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Deng, H., King, I., Lyu, M.R.: Formal models for expert finding on dblp bibliography data. In: Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, ICDM 2008, pp. 163\u2013172. IEEE Computer Society, Washington, DC, USA (2008)","DOI":"10.1109\/ICDM.2008.29"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Druck, G., Mann, G., McCallum, A.: Learning from labeled features using generalized expectation criteria. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, pp. 595\u2013602. ACM, New York (2008)","DOI":"10.1145\/1390334.1390436"},{"key":"1_CR13","unstructured":"Firdhous, M.: Automating legal research through data mining. CoRR, abs\/1211.1861 (2012)"},{"key":"1_CR14","unstructured":"Frank, E., Paynter, G.W., Witten, I.H., Gutwin, G., Nevill-Manning, C.G.: Domain-specific keyphrase extraction. In: IJCAI (1999)"},{"key":"1_CR15","first-page":"2001","volume":"11","author":"K Ganchev","year":"2010","unstructured":"Ganchev, K., Gra\u00e7a, J., Gillenwater, J., Taskar, B.: Posterior regularization for structured latent variable models. J. Mach. Learn. Res. 11, 2001\u20132049 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Gollapalli, S.D., Caragea, C.: Extracting keyphrases from research papers using citation networks. In: AAAI, pp. 1629\u20131635 (2014)","DOI":"10.1609\/aaai.v28i1.8946"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Gollapalli, S.D., Caragea, C., Mitra, P., Giles, C.L.: Researcher homepage classification using unlabeled data. In: Proceedings of the 22nd International Conference on World Wide Web, WWW 2013, pp. 471\u2013482. International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland (2013)","DOI":"10.1145\/2488388.2488430"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Gollapalli, S.D., Giles, C.L., Mitra, P., Caragea, C.: On identifying academic homepages for digital libraries. In: Proceedings of the 11th Annual International ACM\/IEEE Joint Conference on Digital Libraries, JCDL 2011, pp. 123\u2013132. ACM, New York (2011)","DOI":"10.1145\/1998076.1998099"},{"key":"1_CR19","unstructured":"Gollapalli, S.D., Mitra, P., Giles, C.L.: Learning to rank homepages for researcher-name queries. In: SIGIR Workshop on Entity Oriented Search (2011)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Gollapalli, S.D., Mitra, P., Giles, C.L.: Ranking experts using author-document-topic graphs. In: Proceedings of the 13th ACM\/IEEE-CS Joint Conference on Digital libraries, JCDL 2013, pp. 87\u201396, ACM, New York (2011)","DOI":"10.1145\/2467696.2467707"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Gollapalli, S.D., Qi, Y., Mitra, P., Giles, C.L.: Extracting researcher metadata with labeled features. In: SDM, pp. 740\u2013748 (2014)","DOI":"10.1137\/1.9781611973440.85"},{"issue":"Suppl 1","key":"1_CR22","doi-asserted-by":"publisher","first-page":"5228","DOI":"10.1073\/pnas.0307752101","volume":"101","author":"TL Griffiths","year":"2004","unstructured":"Griffiths, T.L., Steyvers, M.: Finding scientific topics. Proc. Natl. Acad. Sci. U.S.A. 101(Suppl 1), 5228\u20135235 (2004)","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Hammouda, K.M., Matute, D.N., Kamel, M.S.: Corephrase: keyphrase extraction for document clustering. In: Machine Learning and Data Mining in Pattern Recognition (2005)","DOI":"10.1007\/11510888_26"},{"key":"1_CR24","unstructured":"Han, H., Giles, C.L., Manavoglu, E., Zha, H., Zhang, Z., Fox, E.A.: Automatic document metadata extraction using support vector machines. In: Proceedings of the 3rd ACM\/IEEE-CS Joint Conference on Digital libraries, JCDL 2003, pp. 37\u201348. IEEE Computer Society, Washington, DC, USA (2003)"},{"key":"1_CR25","volume-title":"Data Mining: Concepts and Techniques","author":"J Han","year":"2005","unstructured":"Han, J.: Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers Inc., Burlington (2005)"},{"key":"1_CR26","unstructured":"Haveliwala, T., Kamvar, S., Klein, D., Manning, C., Golub, G.: Computing pagerank using power extrapolation. Number 2003\u201345. Stanford (2003)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"He, Q., Chen, B., Pei, J., Qiu, B., Mitra, P., Giles, C.L.: Detecting topic evolution in scientific literature: how can citations help? In: CIKM, pp. 957\u2013966 (2009)","DOI":"10.1145\/1645953.1646076"},{"key":"1_CR28","unstructured":"Heinrich, G.: Parameter estimation for text analysis. Technical report (2008)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999, pp. 50\u201357. ACM, New York (1999)","DOI":"10.1145\/312624.312649"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Hulth, A.: Improved automatic keyword extraction given more linguistic knowledge. In: EMNLP, pp. 216\u2013223 (2003)","DOI":"10.3115\/1119355.1119383"},{"issue":"3","key":"1_CR31","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1093\/pan\/mpp006","volume":"17","author":"A Jakulin","year":"2009","unstructured":"Jakulin, A., Buntine, W., La Pira, T., Brasher, H.: Analyzing the U.S. senate in 2003: similarities, clusters, and blocs. Polit. Anal. 17(3), 10 (2009)","journal-title":"Polit. Anal."},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Jones, S., Staveley, M.S.: Phrasier: a system for interactive document retrieval using keyphrases. In: SIGIR (1999)","DOI":"10.1145\/312624.312671"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Kataria, S., Kumar, K.S., Rastogi, R., Sen, P., Sengamedu, S.H.: Entity disambiguation with hierarchical topic models. In: KDD, pp. 1037\u20131045 (2011)","DOI":"10.1145\/2020408.2020574"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Kataria, S., Mitra, P., Bhatia, S.: Utilizing context in generative bayesian models for linked corpus. In: AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7520"},{"key":"1_CR35","unstructured":"Kataria, S., Mitra, P., Caragea, C., Giles, C.L.: Context sensitive topic models for author influence in document networks. In: IJCAI, pp. 2274\u20132280 (2011)"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Kim, S.N., Kan, M.-Y.: Re-examining automatic keyphrase extraction approaches in scientific articles. In: Proceedings of the Workshop on Multiword Expressions: Identification, Interpretation, Disambiguation and Applications, MWE 2009 (2009)","DOI":"10.3115\/1698239.1698242"},{"issue":"3","key":"1_CR37","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1007\/s10579-012-9210-3","volume":"47","author":"SN Kim","year":"2013","unstructured":"Kim, S.N., Medelyan, O., Kan, M.-Y., Baldwin, T.: Automatic keyphrase extraction from scientific articles. Lang. Resour. Eval. 47(3), 723\u2013742 (2013)","journal-title":"Lang. Resour. Eval."},{"key":"1_CR38","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, ICML 2001, pp. 282\u2013289, Morgan Kaufmann Publishers Inc., San Francisco (2001)"},{"key":"1_CR39","unstructured":"Li, H., Councill, I.G., Bolelli, L., Zhou, D., Song, Y., Lee, W.-C., Sivasubramaniam, A., Giles, C.L.: Citeseerx: a scalable autonomous scientific digital library. In: Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale 2006. ACM, New York (2006)"},{"key":"1_CR40","volume-title":"Biological Data Mining and Its Applications in Healthcare","author":"X Li","year":"2013","unstructured":"Li, X., Ng, S.-K., Wang, J.T.L.: Biological Data Mining and Its Applications in Healthcare, 1st edn. World Scientific Publishing Co., Inc., Singapore (2013)","edition":"1"},{"key":"1_CR41","volume-title":"Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data (Data-Centric Systems and Applications)","author":"B Liu","year":"2006","unstructured":"Liu, B.: Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data (Data-Centric Systems and Applications). Springer-Verlag New York Inc., New York (2006)"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Liu, F., Pennell, D., Liu, F., Liu, Y.: Unsupervised approaches for automatic keyword extraction using meeting transcripts. In: Proceedings of NAACL 2009, pp. 620\u2013628 (2009)","DOI":"10.3115\/1620754.1620845"},{"issue":"1","key":"1_CR43","first-page":"1","volume":"39","author":"X Liu","year":"2005","unstructured":"Liu, X., Croft, W.B.: Statistical language modeling for information retrieval. ARIST 39(1), 1\u201331 (2005)","journal-title":"ARIST"},{"key":"1_CR44","first-page":"955","volume":"11","author":"GS Mann","year":"2010","unstructured":"Mann, G.S., McCallum, A.: Generalized expectation criteria for semi-supervised learning with weakly labeled data. J. Mach. Learn. Res. 11, 955\u2013984 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR45","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to Information Retrieval. Cambridge University Press, New York (2008)"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Marujo, L., Ribeiro, R., de Matos, D.M., Neto, J.P., Gershman, A., Carbonell, J.G.: Key phrase extraction of lightly filtered broadcast news. CoRR (2013)","DOI":"10.1007\/978-3-642-32790-2_35"},{"key":"1_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/978-3-540-77094-7_41","volume-title":"Asian Digital Libraries","author":"TD Nguyen","year":"2007","unstructured":"Nguyen, T.D., Kan, M.-Y.: Keyphrase extraction in scientific publications. In: Goh, D.H.-L., Cao, T.H., S\u00f8lvberg, I.T., Rasmussen, E. (eds.) ICADL 2007. LNCS, vol. 4822, pp. 317\u2013326. Springer, Heidelberg (2007)"},{"issue":"4","key":"1_CR48","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1177\/0165551506065785","volume":"32","author":"J-L Ortega-Priego","year":"2006","unstructured":"Ortega-Priego, J.-L., Aguillo, I.F., Prieto-Valverde, J.A.: Longitudinal study of contents and elements in the scientific web environment. J. Inf. Sci. 32(4), 344\u2013351 (2006)","journal-title":"J. Inf. Sci."},{"key":"1_CR49","unstructured":"Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: Bringing order to the web. Technical report (1999)"},{"issue":"12","key":"1_CR50","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1002\/int.20448","volume":"25","author":"N Pudota","year":"2010","unstructured":"Pudota, N., Dattolo, A., Baruzzo, A., Ferrara, F., Tasso, C.: Automatic keyphrase extraction and ontology mining for content-based tag recommendation. Int. J. Intell. Syst. 25(12), 1158\u20131186 (2010)","journal-title":"Int. J. Intell. Syst."},{"key":"1_CR51","volume-title":"Introduction to Modern Information Retrieval","author":"G Salton","year":"1986","unstructured":"Salton, G., McGill, M.J.: Introduction to Modern Information Retrieval. McGraw-Hill Inc., New York (1986)"},{"issue":"3","key":"1_CR52","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1561\/1900000003","volume":"1","author":"S Sarawagi","year":"2008","unstructured":"Sarawagi, S.: Information extraction. Found. Trends Databases 1(3), 261\u2013377 (2008)","journal-title":"Found. Trends Databases"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Tang, J., Jin, R., Zhang, J.: A topic modeling approach and its integration into the random walk framework for academic search. In: Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, ICDM 2008, pp. 1055\u20131060. IEEE Computer Society, Washington, DC, USA (2008)","DOI":"10.1109\/ICDM.2008.71"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Tang, J., Zhang, J., Yao, L., Li, J., Zhang, L., Su, Z.: Arnetminer: extraction and mining of academic social networks. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery nd Data Mining, KDD 2008, pp. 990\u2013998. ACM, New York (2008)","DOI":"10.1145\/1401890.1402008"},{"key":"1_CR55","unstructured":"Teregowda, P.B., Councill, I.G., Fern\u00e1ndez, R.J.P., Khabsa, M., Zheng, S., Giles, C.L.: Seersuite: developing a scalable and reliable application framework for building digital libraries by crawling the web. In: Proceedings of the 2010 USENIX Conference on Web Application Development WebApps 2010 (2010)"},{"key":"1_CR56","doi-asserted-by":"crossref","unstructured":"Tuarob, S., Pouchard, L.C., Giles, C.L.: Automatic tag recommendation for metadata annotation using probabilistic topic modeling. In: Proceedings of the 13th ACM\/IEEE-CS Joint Conference on Digital Libraries, JCDL 2013, pp. 239\u2013248. ACM (2013)","DOI":"10.1145\/2467696.2467706"},{"key":"1_CR57","doi-asserted-by":"crossref","unstructured":"Wu, J., Williams, K., Chen, H.-H., Khabsa, M., Caragea, C., Ororbia, A., Jordan, D., Giles, C.L.: Citeseerx: Ai in a digital library search engine. In: IAAI (2014)","DOI":"10.1609\/aaai.v28i2.19019"},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Zha, H.: Generic summarization and keyphrase extraction using mutual reinforcement principle and sentence clustering. In: SIGIR (2002)","DOI":"10.1145\/564376.564398"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Zheng, S., Zhou, D., Li, J., Giles, C.L.: Extracting author meta-data from web using visual features. In: Proceedings of the Seventh IEEE International Conference on Data Mining Workshops, ICDMW 2007, pp. 33\u201340. IEEE Computer Society, Washington, DC, USA (2007)","DOI":"10.1109\/ICDMW.2007.59"}],"container-title":["Communications in Computer and Information Science","Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-25485-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T08:08:14Z","timestamp":1700208494000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-25485-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319254845","9783319254852"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-25485-2_1","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"10 December 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RuSSIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russian Summer School in Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nizhniy Novgorod","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2014","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 August 2014","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2014","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"russir2014","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}