Computerlinguistik – Was ist das?

Carstensen, Kai-Uwe; Jekat, Susanne Johanna; Klabunde, Ralf

doi:10.1007/978-3-8274-2224-8_1

Cited by 12 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Biomedizinische Inhalte stehen seit Langem im Fokus von Disziplinen wie Information Retrieval [9] und Computerlinguistik [10], deren Anwendungen oft als "Text Mining" oder "Unstructured Information Management" charakterisiert werden [11,12] Big data, medical language and biomedical terminology systems Abstract A variety of rich terminology systems, such as thesauri, classifications, nomenclatures and ontologies support information and knowledge processing in health care and biomedical research. Nevertheless, human language, manifested as individually written texts, persists as the primary carrier of information, in the description of disease courses or treatment episodes in electronic medical records, and in the description of biomedical research in scientific publications.…”

Section: Die Maschinelle Verarbeitung Natürlicher Sprachementioning

confidence: 99%

Big Data, medizinische Sprache und biomedizinische Ordnungssysteme

Schulz

López-García

2015

Bundesgesundheitsbl.

View full text Add to dashboard Cite

A variety of rich terminology systems, such as thesauri, classifications, nomenclatures and ontologies support information and knowledge processing in health care and biomedical research. Nevertheless, human language, manifested as individually written texts, persists as the primary carrier of information, in the description of disease courses or treatment episodes in electronic medical records, and in the description of biomedical research in scientific publications. In the context of the discussion about big data in biomedicine, we hypothesize that the abstraction of the individuality of natural language utterances into structured and semantically normalized information facilitates the use of statistical data analytics to distil new knowledge out of textual data from biomedical research and clinical routine. Computerized human language technologies are constantly evolving and are increasingly ready to annotate narratives with codes from biomedical terminology. However, this depends heavily on linguistic and terminological resources. The creation and maintenance of such resources is labor-intensive. Nevertheless, it is sensible to assume that big data methods can be used to support this process. Examples include the learning of hierarchical relationships, the grouping of synonymous terms into concepts and the disambiguation of homonyms. Although clear evidence is still lacking, the combination of natural language technologies, semantic resources, and big data analytics is promising.

show abstract

Section: Die Maschinelle Verarbeitung Natürlicher Sprachementioning

confidence: 99%

Big Data, medizinische Sprache und biomedizinische Ordnungssysteme

Schulz

López-García

2015

Bundesgesundheitsbl.

View full text Add to dashboard Cite

show abstract

“…The individual courses were planned in accordance with the sequence of topics in standard textbooks such as Jurafsky and Martin (2000) and Carstensen et al (2004) for Introduction to Computational Linguistics, Schöning (2001) for Formal Foundations, and Meibauer et al (2002) for Foundations of Linguistic Analysis. In Introduction to Programming we used a hands-on manuscript (Demleitner, unpublished).…”

Section: Analysis Of the Syllabimentioning

confidence: 99%

“…Specific topics are: dealing with ambiguities, approximation of linguistic regularities, and the relation of language and knowledge; some applications of Computational Linguistics are also introduced. Mandatory readings are selected sections from Jurafsky & Martin (2000), complemented by chapters from Carstensen et al (2004) and Bird et al (forthcoming).…”

Section: Introduction To Computational Linguisticsmentioning

confidence: 99%

See 1 more Smart Citation

Freshmen's CL curriculum

Zinsmeister

2008

Proceedings of the Third Workshop on Issues in Teaching Computational Linguistics - TeachCL '08

View full text Add to dashboard Cite

In the course of the European Bologna accord on higher education, German universities have been reorganizing their traditional "Magister" and "Diplom" studies into modularized bachelor's and master's programs. This revision provides a chance to update the programs. In this paper we introduce the curriculum of a first semester B.A. program in Computational Linguistics which was taught for the first time last semester. In addition, we analyze the syllabi of four mandatory courses of the first semester to identify overlapping content which led to redundancies. We suggest for future semesters to reorganize the schedules in a way that students encounter recurring topics iteratively in a constructive way.

show abstract

“…(Falko L2, Text 36) (lb ) Eine Vielzahl syntaktischer Mittel, z.B. Relativsatz, Präpositionalphrase, Genitivergänzung, adjektivische Modifikationen, ermöglichen (Manning & Schütze 1999;Carstensen et al 2004). Bereits das automatische Tokenisieren kann problematisch sein.…”

Section: Kategorisierung Und Quantitative Analyseunclassified

Das Zusammenspiel von qualitativen und quantitativen Methoden in der Korpuslinguistik

Lüdeling¹

Sprachkorpora - Datenmengen Und Erkenntnisfortschritt

View full text Add to dashboard Cite

Es gibt viele linguistische Forschungsfragen, für deren Beantwortung man Korpusdaten qualitativ und quantitativ auswerten möchte. Beide Auswertungsmethoden können sich auf den Korpustext, aber auch auf Anntotationsebenen beziehen. Jede Art von Annotation, also Kategorisierung, stellt einen kontrollierten und notwendigen Informationsverlust dar. Das bedeutet, dass jede Art von Kategorisierung auch eine Interpretation der Daten ist. In den meisten großen Korpora wird zu jeder vorgesehenen Anntotationsebene, wie z. B. Wortart-Ebene oder Lemma-Ebene, genau eine Interpretation angeboten. In den letzten Jahren haben sich neben den großen,,flach" annotierten Korpora Korpusmodelle herausgebildet, mit denen man konfligierende Informationen kodieren kann, die so genannten Mehrebenen-Modelle (multilevel standoff corpora), in denen alle Annotationsebenen unabhängig vom Text gespeichert werden und nur auf bestimmte Textanker verweisen. Ich argumentiere anhand der Fehlerannotation in einem Lemerkorpus dafür, dass zumindest Korpora, in denen es stark variierende Annotationsbedürfnisse und umstrittene Analysen geben kann, davon profitieren, in Mehrebenen-Modellen kodiert zu werden.

show abstract

Computerlinguistik – Was ist das?

Cited by 12 publications

References 0 publications

Big Data, medizinische Sprache und biomedizinische Ordnungssysteme

Big Data, medizinische Sprache und biomedizinische Ordnungssysteme

Freshmen's CL curriculum

Das Zusammenspiel von qualitativen und quantitativen Methoden in der Korpuslinguistik

Contact Info

Product

Resources

About