-
-
Author(s): Matuschek, Michael; Gurevych, Iryna
Title: High performance word sense alignment by joint modeling of sense distance and gloss similarity
In: Tsujii, Junichi; Hajic, Jan (Hrsg.): Proceedings of COLING 2014: Technical papers, Stroudsburg; PA: Association for Computational Linguistics, 2014 , S. 245-256
URL: http://www.aclweb.org/anthology/C/C14/C14-1025.pdf
Publication Type: 4. Beiträge in Sammelbänden; Tagungsband/Konferenzbeitrag/Proceedings
Language: Englisch
Keywords: Algorithmus; Automatisierung; Computerlinguistik; Nachschlagewerk; Online; Semantik; Sinn; Wort
Abstract: In this paper, we present a machine learning approach for word sense alignment (WSA) which combines distances between senses in the graph representations of lexical-semantic resources with gloss similarities. In this way, we significantly outperform the state of the art on each of the four datasets we consider. Moreover, we present two novel datasets for WSA between Wiktionary and Wikipedia in English and German. The latter dataset in not only of unprecedented size, but also created by the large community of Wiktionary editors instead of expert annotators, making it an interesting subject of study in its own right as the first crowdsourced WSA dataset. We will make both datasets freely available along with our computed alignments. (DIPF/Orig.)
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Botte, Alexander
Title: The relevance of the EERQI framework in the light of future perspectives. Enhancing the visibility and detection of European research publications
In: Gogolin, Ingrid;Aström, Fredrik;Hansen, Antje (Hrsg.): Assessing quality in European Educational Research: Indicators and approaches, Wiesbaden: Springer VS, 2014 (Research), S. 184-196
DOI: 10.1007/978-3-658-05968-9
Publication Type: 4. Beiträge in Sammelwerken; Sammelband (keine besondere Kategorie)
Language: Englisch
Keywords: Bewertung; Europäische Union; Forschung; Information Retrieval; Internet; Kommunikation; Messung; Online-Publikation; Open Access; Projekt; Publikation; Qualität; Semantic Web; Wissenschaft; Wissenschaftliche Literatur
Abstract: Das Buch präsentiert Ergebnisse und Perspektiven des EU-Projekts "European Educational Research Quality Indicators (EERQI)" in kondensierter Form. Im Zentrum dabei stehen die entwickelte Suchmaschine, die eingesetzten Verfahren automatischer semantischer Analyse, die Indikatorenentwicklung und die Multilingualität. Der spezielle Beitrag geht auf die perspektivische Tragweite der Projektergebnisse vor dem Hintergrund der Annahme zunehmender Digitalisierung der sozialwissenschaftlichen Publikationskultur ein.
Abstract (english): This book presents results and perspectives of the EU project "European Educational Research Quality Indicators (EERQI)". It is focused on the search engine developped during the project, the approaches of automatic semantic analyses, the development of quality indicators and the aspect of multilinguality. This article focuses on the perspectives of EERQI instruments in the context of future digitalization of the social sciences publication culture.
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Cholakov, Kostadin; Biemann, Chris; Eckle-Kohler, Judith; Gurevych, Iryna
Title: Lexical substitution dataset for German
In: Calzolari, Nicoletta;Choukri,Khalid;Declerck,Thierry;Loftsson,Hrafn;Maegaard,Bente;Mariani,Joseph;Moreno,Asuncion;Odijk,Jan;Piperidis,Stelios (Hrsg.): Proceedings of the 9th International Conference on Language Resources and Evaluations (LREC 2014), Reykjavik: European Language Resources Association, 2014 , S. 1406-1411
URL: http://www.lrec-conf.org/proceedings/lrec2014/pdf/545_Paper.pdf
Publication Type: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language: Englisch
Keywords: Computerlinguistik; Computerunterstütztes Verfahren; Daten; Deutsch; Nachschlagewerk; Online; Sprachanalyse; Synonym; Textanalyse; World wide web 2.0; Wort
Abstract: This article describes a lexical substitution dataset for German. The whole dataset contains 2,040 sentences from the German Wikipedia, with one target word in each sentence. There are 51 target nouns, 51 adjectives, and 51 verbs randomly selected from 3 frequency groups based on the lemma frequency list of the German WaCKy corpus. 200 sentences have been annotated by 4 professional annotators and the remaining sentences by 1 professional annotator and 5 additional annotators who have been recruited via crowdsourcing. The resulting dataset can be used to evaluate not only lexical substitution systems, but also different sense inventories and word sense disambiguation systems.
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Daxenberger, Johannes; Gurevych, Iryna
Title: Automatically detecting corresponding edit-turn-pairs in Wikipedia
In: Association for Computational Linguistics (Hrsg.): Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Short Papers, Stroudsburg; PA: Association for Computational Linguistics, 2014 , S. 187-192
URL: http://anthology.aclweb.org//P/P14/P14-2031.pdf
Publication Type: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language: Englisch
Keywords: Automatisierung; Computerunterstütztes Verfahren; Information; Nachschlagewerk; Online; Soziale Software; Textanalyse; Wissen; World wide web 2.0
Abstract: In this study, we analyze links between edits in Wikipedia articles and turns from their discussion page. Our motivation is to better understand implicit details about the writing process and knowledge flow in collaboratively created resources. Based on properties of the involved edit and turn, we have defined constraints for corresponding edit-turn-pairs. We manually annotated a corpus of 636 corresponding and non-corresponding edit-turn-pairs. Furthermore, we show how our data can be used to automatically identify corresponding edit-turn-pairs. With the help of supervised machine learning, we achieve an accuracy of .87 for this task.
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Flekova, Lucie; Ferschke, Oliver; Gurevych, Iryna
Title: What makes a good biography? Multidimensional quality analysis based on Wikipedia article feedback data
In: IW3C2 (Hrsg.): Proceedings of the 23rd International World Wide Web Conference (WWW 2014), Geneva: International World Wide Web Conferences Steering Committee, 2014 , S. 855-866
DOI: 10.1145/2566486.2567972
URL: http://dl.acm.org/citation.cfm?doid=2566486.2567972
Publication Type: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language: Englisch
Keywords: Bewertung; Biografie; Feedback; Information; Information Retrieval; Inhaltsanalyse; Nachschlagewerk; Online; Qualität; Qualitätssicherung; World wide web 2.0
Abstract:
With more than 22 million articles, the largest collaborative knowledge resource never sleeps, experiencing several article edits every second. Over one fifth of these articles describes individual people, the majority of which are still alive. Such articles are, by their nature, prone to corruption and vandalism. Manual quality assurance by experts can barely cope with this massive amount of data. Can it be effectively replaced by feedback from the crowd? Can we provide meaningful support for quality assurance with automated text processing techniques? Which properties of the articles should then play a key role in the machine learning algorithms and why? In this paper, we study the user-perceived quality of Wikipedia articles based on a novel Wikipedia user feedback dataset. In contrast to previous work on quality assessment which mostly relied on judgements of active Wikipedia authors, we analyze ratings of ordinary Wikipedia users along four quality dimensions (complete, well written, trustworthy and objective). We first present an empirical analysis of the novel dataset with over 36 million Wikipedia article ratings. We then select a subset of biographical articles and perform classification experiments to predict their quality ratings along each of the dimensions, exploring multiple linguistic, surface and network properties of the rated articles. Additionally, we study the classification performance and differences for the biographies of living and dead people as well as those for men and women. We demonstrate the effectiveness of our approach by the F1 scores of 0.94, 0.89, 0.73, and 0.73 for the dimensions complete, well written, trustworthy, and objective. Based on the results, we believe that the quality assessment of big textual data can be effectively supported by current text classification and language processing tools.
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Griesbaum, Joachim; Mahrholz, Nadine; Bertram, Jens; Pietras, Nadine; Rittberger, Marc
Title: Information behavior in the Social Web. An overview of the German Educational Domain
In: iSchools (Hrsg.): iConference 2014 Proceedings, Chicago; IL: iSchools, 2014 , S. 356-371
DOI: 10.9776/14113
URL: http://hdl.handle.net/2142/47297
Publication Type: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language: Englisch
Keywords: Analyse; Bildung; Bildungsangebot; Deutschland; Empirische Forschung; Gemeinschaft; Information; Informationsverhalten; Kommunikation; Medienangebot; Nutzerverhalten; Nutzung; Online; Qualität; Soziales Netzwerk; Soziale Software; Web log; World wide web 2.0
Abstract: This paper explores participative Social Information Behavior in the educational domain. The goal is to capture a picture of current information practices in the Social Web. The focus is on the "places" and the scale of the Social Web in the domain, the communication dynamics and structure of communities and the specificities, quality, pragmatics and success of communication processes. The paper describes the concept and current implementation status of an online analysis approach and system that tries to answer these questions. Furthermore, first empirical results are presented. Data indicates that participative Social Information Behavior is of relevance in the domain: The volume of openly accessible user-generated content is impressive. The basic characteristics of analyzed forums suggest that such websites resemble sustainable knowledge building communities. Pre-tests regarding the analysis of communication processes denote that generated content can often be seen as a valuable information resource.
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Miller, Tristan; Gurevych, Iryna
Title: WordNet-Wikipedia-Wiktionary. Construction of a three-way alignment
In: Calzolari, Nicoletta;Choukri,Khalid;Declerck,Thierry;Loftsson,Hrafn;Maegaard,Bente;Mariani,Joseph;Moreno,Asuncion;Odijk,Jan;Piperidis,Stelios (Hrsg.): Proceedings of the 9th International Conference on Language Resources and Evaluations (LREC 2014), Reykjavik: European Language Resources Association, 2014 , S. 2094-2100
URL: http://www.lrec-conf.org/proceedings/lrec2014/pdf/4_Paper.pdf
Publication Type: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Language: Englisch
Keywords: Analyse; Computerlinguistik; Evaluation; Nachschlagewerk; Online; Semantik; World wide web 2.0; Wort; Wörterbuch
Abstract: The coverage and quality of conceptual information contained in lexical semantic resources is crucial for many tasks in natural language processing. Automatic alignment of complementary resources is one way of improving this coverage and quality; however, past attempts have always been between pairs of specific resources. In this paper we establish some set-theoretic conventions for describing concepts and their alignments, and use them to describe a method for automatically constructing n-way alignments from arbitrary pairwise alignments. We apply this technique to the production of a three-way alignment from previously published WordNet-Wikipedia and WordNet-Wiktionary alignments. We then present a quantitative and informal qualitative analysis of the aligned resource. The three-way alignment was found to have greater coverage, an enriched sense representation, and coarser sense granularity than both the original resources and their pairwise alignments, though this came at the cost of accuracy. An evaluation of the induced word sense clusters in a word sense disambiguation task showed that they were no better than random clusters of equivalent granularity. However, use of the alignments to enrich a sense inventory with additional sense glosses did significantly improve the performance of a baseline knowledge-based WSD algorithm.
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Neß, Harry
Title: KMU.KOM. Die eVersion zur Verbesserung des kompetenzbuchgestützten Personalmanagements
In: Elsholz, Uwe; Rohs, Matthias (Hrsg.): E-Portfolios für das lebenslange Lernen: Konzepte und Perspektiven, Bielefeld: Bertelsmann, 2014 , S. 115-131
Publication Type: 4. Beiträge in Sammelwerken; Sammelband (keine besondere Kategorie)
Language: Deutsch
Keywords: Deutschland; Hessen; Informelles Lernen; Klein- und Mittelbetrieb; Kompetenz; Lebenslanges Lernen; Nutzung; Online; Personalentwicklung; Personalmanagement; Portfolio
Abstract: Das [in diesem Beitrag] vorgestellte Instrument dient der Verbesserung des Personalmanagements und ist für den Einsatz in kleinen und mittleren Unternehmen (KMU) konzipiert. Ziel des Kompetenzbuchs ist die Sichtbarmachung auch informell erworbener Kompetenzen und deren Abgleich durch Selbst- und Fremdbewertung vor dem Hintergrund betrieblicher Anforderungen. [Der] elektronischen Umsetzung liegt [...] bereits eine papierbasierte Fassung zugrunde, wobei durch die elektronische Umsetzung zusätzliche Möglichkeiten erschlossen werden und eine leichtere Nutzbarkeit erreicht wurde. (DIPF/Orig.)
DIPF-Departments: Struktur und Steuerung des Bildungswesens
-
-
Author(s): Vorndran, Angela
Title: Guidelines for transfer of the EERQI prototype framework to other social and economic sciences and humanities
In: Gogolin, Ingrid; Åström, Fredrik; Hansen, Antje (Hrsg.): Assessing quality in European Educational Research: Indicators and approaches, Wiesbaden: Springer VS, 2014 , S. 165-183
Publication Type: 4. Beiträge in Sammelwerken; Sammelband (keine besondere Kategorie)
Language: Englisch
Keywords: Bildungsforschung; Gewohnheit; Internet; Online-Publikation; Politikwissenschaft; Projekt; Publikation; Publizieren; Sozialwissenschaften; Transfer; Wissenschaftliche Literatur; Wissenschaftsdisziplin
Abstract: The tools constituting the EERQI framework were developed within the research field of educational science: A peer review exercise was applied involving educational scientists and document evaluation procedures for educational research texts. To enable adaptation of the framework to different disciplinary contexts, a transferability exercise was part of the work. This chapter examines the possibilities of transferring the EERQI framework to the research field of political science taking into consideration the similarities and differences in publication cultures of both fields and developing guidelines for the transfer.
DIPF-Departments: Informationszentrum Bildung
-
-
Author(s): Hirschmann, Doris
Title: Suche - Recherche nach Massive Open Online Courses (MOOCs)
Published: Frankfurt am Main: Deutsches Institut für Internationale Pädagogische Forschung, 2014
URL: http://www.bildungsserver.de/Suche-Recherche-nach-Massive-Open-Online-Courses-MOOCs--11046.html
Publication Type: 5. Arbeits- und Diskussionspapiere; Online Dossiers (DBS)
Language: Deutsch
Keywords: Bildungsangebot; Digitale Medien; E-Learning; Fernstudium; Kurs; Lehrveranstaltung; Online; Open Access; Open Education; Quellensammlung; Recherche
Abstract: Informationen darüber was MOOCs sind und die Diskussion über ihre Qualität, ihren Nutzen und das Pro und Contra dieser Entwicklung sind beim Deutschen Bildungsserver vielfältig vorhanden. In der rechten Spalte finden sich Hinweise auf diese Informationen. Dieses Dossier widmet sich nun der Frage ``Wo kann ich aktuell stattfindende MOOCs finden?´´ und bietet daher ausschließlich eine Sammlung an Internetadressen, die entweder zu einer Suchfunktion speziell nach MOOCs führen oder zu aktuellen Listen mit derzeit laufenden oder bald beginnenden MOOCs.
DIPF-Departments: Informationszentrum Bildung