Refine
Document Type
- Article (6) (remove)
Has Fulltext
- yes (6)
Keywords
- Grammatik (3)
- Deutsch (2)
- Kongressbericht (2)
- Korpus <Linguistik> (2)
- Mentaler Wortschatz (2)
- Annotation (1)
- Automatic recognition of speech (1)
- Automatische Sprachanalyse (1)
- Automatische Spracherkennung (1)
- Direct speech (1)
Publicationstate
- Veröffentlichungsversion (4)
- Postprint (1)
Reviewstate
- Peer-Review (3)
- (Verlags)-Lektorat (1)
- Verlags-Lektorat (1)
Publisher
- Institut für Deutsche Sprache (2)
- Erich Schmidt Verlag (1)
- Peter Lang (1)
- de Gruyter (1)
Vom 14. bis 16. März fand im Congress Center Rosengarten in Mannheim die 53. Jahrestagung des Instituts für Deutsche Sprache (IDS) statt, die sich in diesem Jahr mit dem Lexikon und dessen Komplexität und Dynamik beschäftigte. Im Mittelpunkt standen neue Perspektiven auf das Lexikon und die Lexikonforschung nach der empirischen Wende, die das Bild vom Wortschatz deutlich verändert und den Blick darauf erweitert hat. Lexikontheoretiker und Lexikografen arbeiten heute u.a. mit quantitativen korpuslinguistischen Methoden und berücksichtigen Forschungsergebnisse und -methoden angrenzender Disziplinen wie der Psycholinguistik, wodurch auch neuartige Konzepte ins Blickfeld rücken. Das Inventar lexikalischer Einheiten beschränkt sich nicht mehr nur auf Wörter, sondern wurde durch konstruktionsartige Einheiten und semiabstrakte lexikalische Muster ergänzt.
Bericht von der Dritten Internationalen Konferenz „Grammatik und Korpora“, Mannheim, 22. - 24.9.2009
(2009)
The paper explores factors that influence the distribution of constituent words of compounds over the head and modifier position. The empirical basis for the study is a large database of German compounds, annotated with respect to the morphological structure of the compound and the semantic category of the constituents. The study shows that the polysemy of the constituent word, its constituent family size, and its semantic category account for tendencies of the constituent word to occur in either modifier or head position. Furthermore, the paper explores the degree to which the semantic category combination of head and modifier word, e.g., x=substance and y=artifact, indicates the semantic relation between the constituents, e.g., y_consists_of_x.
This contribution presents a quantitative approach to speech, thought and writing representation (ST&WR) and steps towards its automatic detection. Automatic detection is necessary for studying ST&WR in a large number of texts and thus identifying developments in form and usage over time and in different types of texts. The contribution summarizes results of a pilot study: First, it describes the manual annotation of a corpus of short narrative texts in relation to linguistic descriptions of ST&WR. Then, two different techniques of automatic detection – a rule-based and a machine learning approach – are described and compared. Evaluation of the results shows success with automatic detection, especially for direct and indirect ST&WR.
Automatic recognition of speech, thought, and writing representation in German narrative texts
(2013)
This article presents the main results of a project, which explored ways to recognize and classify a narrative feature—speech, thought, and writing representation (ST&WR)—automatically, using surface information and methods of computational linguistics. The task was to detect and distinguish four types—direct, free indirect, indirect, and reported ST&WR—in a corpus of manually annotated German narrative texts. Rule-based as well as machine-learning methods were tested and compared. The results were best for recognizing direct ST&WR (best F1 score: 0.87), followed by indirect (0.71), reported (0.58), and finally free indirect ST&WR (0.40). The rule-based approach worked best for ST&WR types with clear patterns, like indirect and marked direct ST&WR, and often gave the most accurate results. Machine learning was most successful for types without clear indicators, like free indirect ST&WR, and proved more stable. When looking at the percentage of ST&WR in a text, the results of machine-learning methods always correlated best with the results of manual annotation. Creating a union or intersection of the results of the two approaches did not lead to striking improvements. A stricter definition of ST&WR, which excluded borderline cases, made the task harder and led to worse results for both approaches.