-
Hauer, M.: Tiefenindexierung im Bibliothekskatalog : 17 Jahre intelligentCAPTURE (2019)
0.05
0.052551936 = product of:
0.10510387 = sum of:
0.10510387 = product of:
0.1576558 = sum of:
0.08467 = weight(_text_:i in 5629) [ClassicSimilarity], result of:
0.08467 = score(doc=5629,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.50006545 = fieldWeight in 5629, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.09375 = fieldNorm(doc=5629)
0.07298581 = weight(_text_:22 in 5629) [ClassicSimilarity], result of:
0.07298581 = score(doc=5629,freq=2.0), product of:
0.15720168 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.044891298 = queryNorm
0.46428138 = fieldWeight in 5629, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.09375 = fieldNorm(doc=5629)
0.6666667 = coord(2/3)
0.5 = coord(1/2)
- Content
- Vgl.: https://www.b-i-t-online.de/heft/2019-02-index.php.
- Source
- B.I.T.online. 22(2019) H.2, S.163-166
-
Busch, D.: Domänenspezifische hybride automatische Indexierung von bibliographischen Metadaten (2019)
0.03
0.026275968 = product of:
0.052551936 = sum of:
0.052551936 = product of:
0.0788279 = sum of:
0.042335 = weight(_text_:i in 5628) [ClassicSimilarity], result of:
0.042335 = score(doc=5628,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.25003272 = fieldWeight in 5628, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.046875 = fieldNorm(doc=5628)
0.036492907 = weight(_text_:22 in 5628) [ClassicSimilarity], result of:
0.036492907 = score(doc=5628,freq=2.0), product of:
0.15720168 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.044891298 = queryNorm
0.23214069 = fieldWeight in 5628, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.046875 = fieldNorm(doc=5628)
0.6666667 = coord(2/3)
0.5 = coord(1/2)
- Content
- Vgl.: https://www.b-i-t-online.de/heft/2019-06-index.php.
- Source
- B.I.T.online. 22(2019) H.6, S.465-469
-
Martins, A.L.; Souza, R.R.; Ribeiro de Mello, H.: ¬The use of noun phrases in information retrieval : proposing a mechanism for automatic classification (2014)
0.02
0.019237336 = product of:
0.03847467 = sum of:
0.03847467 = product of:
0.057712007 = sum of:
0.033383403 = weight(_text_:c in 1441) [ClassicSimilarity], result of:
0.033383403 = score(doc=1441,freq=4.0), product of:
0.15484828 = queryWeight, product of:
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.044891298 = queryNorm
0.21558782 = fieldWeight in 1441, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.03125 = fieldNorm(doc=1441)
0.024328604 = weight(_text_:22 in 1441) [ClassicSimilarity], result of:
0.024328604 = score(doc=1441,freq=2.0), product of:
0.15720168 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.044891298 = queryNorm
0.15476047 = fieldWeight in 1441, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.03125 = fieldNorm(doc=1441)
0.6666667 = coord(2/3)
0.5 = coord(1/2)
- Abstract
- This paper presents a research on syntactic structures known as noun phrases (NP) being applied to increase the effectiveness and efficiency of the mechanisms for the document's classification. Our hypothesis is the fact that the NP can be used instead of single words as a semantic aggregator to reduce the number of words that will be used for the classification system without losing its semantic coverage, increasing its efficiency. The experiment divided the documents classification process in three phases: a) NP preprocessing b) system training; and c) classification experiments. In the first step, a corpus of digitalized texts was submitted to a natural language processing platform1 in which the part-of-speech tagging was done, and them PERL scripts pertaining to the PALAVRAS package were used to extract the Noun Phrases. The preprocessing also involved the tasks of a) removing NP low meaning pre-modifiers, as quantifiers; b) identification of synonyms and corresponding substitution for common hyperonyms; and c) stemming of the relevant words contained in the NP, for similitude checking with other NPs. The first tests with the resulting documents have demonstrated its effectiveness. We have compared the structural similarity of the documents before and after the whole pre-processing steps of phase one. The texts maintained the consistency with the original and have kept the readability. The second phase involves submitting the modified documents to a SVM algorithm to identify clusters and classify the documents. The classification rules are to be established using a machine learning approach. Finally, tests will be conducted to check the effectiveness of the whole process.
- Source
- Knowledge organization in the 21st century: between historical patterns and future prospects. Proceedings of the Thirteenth International ISKO Conference 19-22 May 2014, Kraków, Poland. Ed.: Wieslaw Babik
-
Mödden, E.: Inhaltserschließung im Zeitalter von Suchmaschinen und Volltextsuche (2018)
0.01
0.011759723 = product of:
0.023519445 = sum of:
0.023519445 = product of:
0.07055833 = sum of:
0.07055833 = weight(_text_:i in 5625) [ClassicSimilarity], result of:
0.07055833 = score(doc=5625,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.41672117 = fieldWeight in 5625, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.078125 = fieldNorm(doc=5625)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Content
- Vgl.: https://www.b-i-t-online.de/heft/2018-01-interview-moedden.pdf.
-
Stankovic, R. et al.: Indexing of textual databases based on lexical resources : a case study for Serbian (2016)
0.01
0.010136919 = product of:
0.020273838 = sum of:
0.020273838 = product of:
0.060821515 = sum of:
0.060821515 = weight(_text_:22 in 2759) [ClassicSimilarity], result of:
0.060821515 = score(doc=2759,freq=2.0), product of:
0.15720168 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.044891298 = queryNorm
0.38690117 = fieldWeight in 2759, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.078125 = fieldNorm(doc=2759)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Date
- 1. 2.2016 18:25:22
-
Siebenkäs, A.; Markscheffel, B.: Conception of a workflow for the semi-automatic construction of a thesaurus for the German printing industry (2015)
0.01
0.009736827 = product of:
0.019473653 = sum of:
0.019473653 = product of:
0.058420956 = sum of:
0.058420956 = weight(_text_:c in 2091) [ClassicSimilarity], result of:
0.058420956 = score(doc=2091,freq=4.0), product of:
0.15484828 = queryWeight, product of:
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.044891298 = queryNorm
0.3772787 = fieldWeight in 2091, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.0546875 = fieldNorm(doc=2091)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Source
- Re:inventing information science in the networked society: Proceedings of the 14th International Symposium on Information Science, Zadar/Croatia, 19th-21st May 2015. Eds.: F. Pehar, C. Schloegl u. C. Wolff
-
Souza, R.R.; Gil-Leiva, I.: Automatic indexing of scientific texts : a methodological comparison (2016)
0.01
0.009407777 = product of:
0.018815555 = sum of:
0.018815555 = product of:
0.056446664 = sum of:
0.056446664 = weight(_text_:i in 4913) [ClassicSimilarity], result of:
0.056446664 = score(doc=4913,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.33337694 = fieldWeight in 4913, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.0625 = fieldNorm(doc=4913)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
-
Gábor, K.; Zargayouna, H.; Tellier, I.; Buscaldi, D.; Charnois, T.: ¬A typology of semantic relations dedicated to scientific literature analysis (2016)
0.01
0.008231806 = product of:
0.016463611 = sum of:
0.016463611 = product of:
0.049390834 = sum of:
0.049390834 = weight(_text_:i in 2933) [ClassicSimilarity], result of:
0.049390834 = score(doc=2933,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.29170483 = fieldWeight in 2933, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.0546875 = fieldNorm(doc=2933)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
-
Glaesener, L.: Automatisches Indexieren einer informationswissenschaftlichen Datenbank mit Mehrwortgruppen (2012)
0.01
0.008109535 = product of:
0.01621907 = sum of:
0.01621907 = product of:
0.04865721 = sum of:
0.04865721 = weight(_text_:22 in 401) [ClassicSimilarity], result of:
0.04865721 = score(doc=401,freq=2.0), product of:
0.15720168 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.044891298 = queryNorm
0.30952093 = fieldWeight in 401, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0625 = fieldNorm(doc=401)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Date
- 11. 9.2012 19:43:22
-
Beyer, C.; Trunk, D.: Automatische Verfahren für die Formalerschließung im Projekt PETRUS (2011)
0.01
0.007868543 = product of:
0.015737087 = sum of:
0.015737087 = product of:
0.04721126 = sum of:
0.04721126 = weight(_text_:c in 1712) [ClassicSimilarity], result of:
0.04721126 = score(doc=1712,freq=2.0), product of:
0.15484828 = queryWeight, product of:
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.044891298 = queryNorm
0.3048872 = fieldWeight in 1712, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.0625 = fieldNorm(doc=1712)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
-
Schöning-Walter, C.: Automatische Erschließungsverfahren für Netzpublikationen : zum Stand der Arbeiten im Projekt PETRUS (2011)
0.01
0.007868543 = product of:
0.015737087 = sum of:
0.015737087 = product of:
0.04721126 = sum of:
0.04721126 = weight(_text_:c in 1714) [ClassicSimilarity], result of:
0.04721126 = score(doc=1714,freq=2.0), product of:
0.15484828 = queryWeight, product of:
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.044891298 = queryNorm
0.3048872 = fieldWeight in 1714, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.0625 = fieldNorm(doc=1714)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
-
Kasprzik, A.: Voraussetzungen und Anwendungspotentiale einer präzisen Sacherschließung aus Sicht der Wissenschaft (2018)
0.01
0.007095843 = product of:
0.014191686 = sum of:
0.014191686 = product of:
0.042575058 = sum of:
0.042575058 = weight(_text_:22 in 5195) [ClassicSimilarity], result of:
0.042575058 = score(doc=5195,freq=2.0), product of:
0.15720168 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.044891298 = queryNorm
0.2708308 = fieldWeight in 5195, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0546875 = fieldNorm(doc=5195)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Abstract
- Große Aufmerksamkeit richtet sich im Moment auf das Potential von automatisierten Methoden in der Sacherschließung und deren Interaktionsmöglichkeiten mit intellektuellen Methoden. In diesem Kontext befasst sich der vorliegende Beitrag mit den folgenden Fragen: Was sind die Anforderungen an bibliothekarische Metadaten aus Sicht der Wissenschaft? Was wird gebraucht, um den Informationsbedarf der Fachcommunities zu bedienen? Und was bedeutet das entsprechend für die Automatisierung der Metadatenerstellung und -pflege? Dieser Beitrag fasst die von der Autorin eingenommene Position in einem Impulsvortrag und der Podiumsdiskussion beim Workshop der FAG "Erschließung und Informationsvermittlung" des GBV zusammen. Der Workshop fand im Rahmen der 22. Verbundkonferenz des GBV statt.
-
Franke-Maier, M.: Anforderungen an die Qualität der Inhaltserschließung im Spannungsfeld von intellektuell und automatisch erzeugten Metadaten (2018)
0.01
0.007095843 = product of:
0.014191686 = sum of:
0.014191686 = product of:
0.042575058 = sum of:
0.042575058 = weight(_text_:22 in 5344) [ClassicSimilarity], result of:
0.042575058 = score(doc=5344,freq=2.0), product of:
0.15720168 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.044891298 = queryNorm
0.2708308 = fieldWeight in 5344, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0546875 = fieldNorm(doc=5344)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Abstract
- Spätestens seit dem Deutschen Bibliothekartag 2018 hat sich die Diskussion zu den automatischen Verfahren der Inhaltserschließung der Deutschen Nationalbibliothek von einer politisch geführten Diskussion in eine Qualitätsdiskussion verwandelt. Der folgende Beitrag beschäftigt sich mit Fragen der Qualität von Inhaltserschließung in digitalen Zeiten, wo heterogene Erzeugnisse unterschiedlicher Verfahren aufeinandertreffen und versucht, wichtige Anforderungen an Qualität zu definieren. Dieser Tagungsbeitrag fasst die vom Autor als Impulse vorgetragenen Ideen beim Workshop der FAG "Erschließung und Informationsvermittlung" des GBV am 29. August 2018 in Kiel zusammen. Der Workshop fand im Rahmen der 22. Verbundkonferenz des GBV statt.
-
Kempf, A.O.: Automatische Indexierung in der sozialwissenschaftlichen Fachinformation : eine Evaluationsstudie zur maschinellen Erschließung für die Datenbank SOLIS (2012)
0.01
0.0070558335 = product of:
0.014111667 = sum of:
0.014111667 = product of:
0.042335 = sum of:
0.042335 = weight(_text_:i in 903) [ClassicSimilarity], result of:
0.042335 = score(doc=903,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.25003272 = fieldWeight in 903, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.046875 = fieldNorm(doc=903)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Imprint
- Berlin : Humboldt-Universität zu Berlin, Philosophische Fakultät I, Institut für Bibliotheks- und Informationswissenschaft
-
Flores, F.N.; Moreira, V.P.: Assessing the impact of stemming accuracy on information retrieval : a multilingual perspective (2016)
0.01
0.0070558335 = product of:
0.014111667 = sum of:
0.014111667 = product of:
0.042335 = sum of:
0.042335 = weight(_text_:i in 3187) [ClassicSimilarity], result of:
0.042335 = score(doc=3187,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.25003272 = fieldWeight in 3187, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.046875 = fieldNorm(doc=3187)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Abstract
- The quality of stemming algorithms is typically measured in two different ways: (i) how accurately they map the variant forms of a word to the same stem; or (ii) how much improvement they bring to Information Retrieval systems. In this article, we evaluate various stemming algorithms, in four languages, in terms of accuracy and in terms of their aid to Information Retrieval. The aim is to assess whether the most accurate stemmers are also the ones that bring the biggest gain in Information Retrieval. Experiments in English, French, Portuguese, and Spanish show that this is not always the case, as stemmers with higher error rates yield better retrieval quality. As a byproduct, we also identified the most accurate stemmers and the best for Information Retrieval purposes.
-
Gil-Leiva, I.: SISA-automatic indexing system for scientific articles : experiments with location heuristics rules versus TF-IDF rules (2017)
0.01
0.0070558335 = product of:
0.014111667 = sum of:
0.014111667 = product of:
0.042335 = sum of:
0.042335 = weight(_text_:i in 3622) [ClassicSimilarity], result of:
0.042335 = score(doc=3622,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.25003272 = fieldWeight in 3622, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.046875 = fieldNorm(doc=3622)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
-
Beckmann, R.; Hinrichs, I.; Janßen, M.; Milmeister, G.; Schäuble, P.: ¬Der Digitale Assistent DA-3 : Eine Plattform für die Inhaltserschließung (2019)
0.01
0.0070558335 = product of:
0.014111667 = sum of:
0.014111667 = product of:
0.042335 = sum of:
0.042335 = weight(_text_:i in 5408) [ClassicSimilarity], result of:
0.042335 = score(doc=5408,freq=2.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.25003272 = fieldWeight in 5408, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.046875 = fieldNorm(doc=5408)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
-
Böhm, A.; Seifert, C.; Schlötterer, J.; Granitzer, M.: Identifying tweets from the economic domain (2017)
0.01
0.006884975 = product of:
0.01376995 = sum of:
0.01376995 = product of:
0.04130985 = sum of:
0.04130985 = weight(_text_:c in 3495) [ClassicSimilarity], result of:
0.04130985 = score(doc=3495,freq=2.0), product of:
0.15484828 = queryWeight, product of:
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.044891298 = queryNorm
0.2667763 = fieldWeight in 3495, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.0546875 = fieldNorm(doc=3495)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
-
Markoff, J.: Researchers announce advance in image-recognition software (2014)
0.01
0.0065738847 = product of:
0.0131477695 = sum of:
0.0131477695 = product of:
0.039443307 = sum of:
0.039443307 = weight(_text_:i in 1875) [ClassicSimilarity], result of:
0.039443307 = score(doc=1875,freq=10.0), product of:
0.16931784 = queryWeight, product of:
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.044891298 = queryNorm
0.23295423 = fieldWeight in 1875, product of:
3.1622777 = tf(freq=10.0), with freq of:
10.0 = termFreq=10.0
3.7717297 = idf(docFreq=2765, maxDocs=44218)
0.01953125 = fieldNorm(doc=1875)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Content
- "Until now, so-called computer vision has largely been limited to recognizing individual objects. The new software, described on Monday by researchers at Google and at Stanford University, teaches itself to identify entire scenes: a group of young men playing Frisbee, for example, or a herd of elephants marching on a grassy plain. The software then writes a caption in English describing the picture. Compared with human observations, the researchers found, the computer-written descriptions are surprisingly accurate. The advances may make it possible to better catalog and search for the billions of images and hours of video available online, which are often poorly described and archived. At the moment, search engines like Google rely largely on written language accompanying an image or video to ascertain what it contains. "I consider the pixel data in images and video to be the dark matter of the Internet," said Fei-Fei Li, director of the Stanford Artificial Intelligence Laboratory, who led the research with Andrej Karpathy, a graduate student. "We are now starting to illuminate it." Dr. Li and Mr. Karpathy published their research as a Stanford University technical report. The Google team published their paper on arXiv.org, an open source site hosted by Cornell University.
In living organisms, webs of neurons in the brain vastly outperform even the best computer-based networks in perception and pattern recognition. But by adopting some of the same architecture, computers are catching up, learning to identify patterns in speech and imagery with increasing accuracy. The advances are apparent to consumers who use Apple's Siri personal assistant, for example, or Google's image search. Both groups of researchers employed similar approaches, weaving together two types of neural networks, one focused on recognizing images and the other on human language. In both cases the researchers trained the software with relatively small sets of digital images that had been annotated with descriptive sentences by humans. After the software programs "learned" to see patterns in the pictures and description, the researchers turned them on previously unseen images. The programs were able to identify objects and actions with roughly double the accuracy of earlier efforts, although still nowhere near human perception capabilities. "I was amazed that even with the small amount of training data that we were able to do so well," said Oriol Vinyals, a Google computer scientist who wrote the paper with Alexander Toshev, Samy Bengio and Dumitru Erhan, members of the Google Brain project. "The field is just starting, and we will see a lot of increases."
Computer vision specialists said that despite the improvements, these software systems had made only limited progress toward the goal of digitally duplicating human vision and, even more elusive, understanding. "I don't know that I would say this is 'understanding' in the sense we want," said John R. Smith, a senior manager at I.B.M.'s T.J. Watson Research Center in Yorktown Heights, N.Y. "I think even the ability to generate language here is very limited." But the Google and Stanford teams said that they expect to see significant increases in accuracy as they improve their software and train these programs with larger sets of annotated images. A research group led by Tamara L. Berg, a computer scientist at the University of North Carolina at Chapel Hill, is training a neural network with one million images annotated by humans. "You're trying to tell the story behind the image," she said. "A natural scene will be very complex, and you want to pick out the most important objects in the image.""
-
Cui, H.; Boufford, D.; Selden, P.: Semantic annotation of biosystematics literature without training examples (2010)
0.01
0.0059014075 = product of:
0.011802815 = sum of:
0.011802815 = product of:
0.035408445 = sum of:
0.035408445 = weight(_text_:c in 3422) [ClassicSimilarity], result of:
0.035408445 = score(doc=3422,freq=2.0), product of:
0.15484828 = queryWeight, product of:
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.044891298 = queryNorm
0.22866541 = fieldWeight in 3422, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.4494052 = idf(docFreq=3817, maxDocs=44218)
0.046875 = fieldNorm(doc=3422)
0.33333334 = coord(1/3)
0.5 = coord(1/2)
- Abstract
- This article presents an unsupervised algorithm for semantic annotation of morphological descriptions of whole organisms. The algorithm is able to annotate plain text descriptions with high accuracy at the clause level by exploiting the corpus itself. In other words, the algorithm does not need lexicons, syntactic parsers, training examples, or annotation templates. The evaluation on two real-life description collections in botany and paleontology shows that the algorithm has the following desirable features: (a) reduces/eliminates manual labor required to compile dictionaries and prepare source documents; (b) improves annotation coverage: the algorithm annotates what appears in documents and is not limited by predefined and often incomplete templates; (c) learns clean and reusable concepts: the algorithm learns organ names and character states that can be used to construct reusable domain lexicons, as opposed to collection-dependent patterns whose applicability is often limited to a particular collection; (d) insensitive to collection size; and (e) runs in linear time with respect to the number of clauses to be annotated.
