Summary of the paper
| Title | Studying Word Sketches for Russian |
|---|---|
| Authors | Maria Khokhlova and Victor Zakharov |
| Abstract | Without any doubt corpora are vital tools for linguistic studies and solutionfor applied tasks. Although corpora opportunities are very useful, there is aneed of another kind of software for further improvement of linguistic researchas it is impossible to process huge amount of linguistic data manually. TheSketch Engine representing itself a corpus tool which takes as input a corpusof any language and corresponding grammar patterns. The paper describes thewriting of Sketch grammar for the Russian language as a part of the SketchEngine system. The system gives information about a word’s collocability onconcrete dependency models, and generates lists of the most frequent phrasesfor a given word based on appropriate models. The paper deals with twodifferent approaches to writing rules for the grammar, based on morphologicalinformation, and also with applying word sketches to the Russian language. Thedata evidences that such results may find an extensive use in various fields oflinguistics, such as dictionary compiling, language learning and teaching,translation (including machine translation), phraseology, information retrievaletc. |
| Language | Statistical and machine learning methods |
| Topics | Tools, systems, applications, Grammar and Syntax, Statistical and machine learning methods |
Full paper  |
Studying Word Sketches for Russian |
| Bibtex | @InProceedings{KHOKHLOVA10.21, author = {Maria Khokhlova and Victor Zakharov}, title = {Studying Word Sketches for Russian}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |