Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{1186170, author = {Kilgarriff, Adam and Rychlý, Pavel and Jakubíček, Miloš and Kovář, Vojtěch and Baisa, Vít and Kocincová, Lucia}, address = {Reykjavik, Iceland}, booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Hrafn Loftsson and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis}, keywords = {corpus; evaluation; collocation}, howpublished = {elektronická verze "online"}, language = {eng}, location = {Reykjavik, Iceland}, isbn = {978-2-9517408-8-4}, pages = {1-8}, publisher = {European Language Resources Association (ELRA)}, title = {Extrinsic Corpus Evaluation with a Collocation Dictionary Task}, url = {http://www.lrec-conf.org/proceedings/lrec2014/summaries/52.html}, year = {2014} }
TY - JOUR ID - 1186170 AU - Kilgarriff, Adam - Rychlý, Pavel - Jakubíček, Miloš - Kovář, Vojtěch - Baisa, Vít - Kocincová, Lucia PY - 2014 TI - Extrinsic Corpus Evaluation with a Collocation Dictionary Task PB - European Language Resources Association (ELRA) CY - Reykjavik, Iceland SN - 9782951740884 KW - corpus KW - evaluation KW - collocation UR - http://www.lrec-conf.org/proceedings/lrec2014/summaries/52.html L2 - http://www.lrec-conf.org/proceedings/lrec2014/summaries/52.html N2 - The NLP researcher or application-builder often wonders ``what corpus should I use, or should I build one of my own? If I build one of my own, how will I know if I have done a good job?'' Currently there is very little help available for them. They are in need of a framework for evaluating corpora. We develop such a framework, in relation to corpora which aim for good coverage of `general language'. The task we set is automatic creation of a publication-quality collocations dictionary. For a sample of 100 headwords of Czech and 100 of English, we identify a gold standard dataset of (ideally) all the collocations that should appear for these headwords in such a dictionary. The datasets are being made available alongside this paper. We then use them to determine precision and recall for a range of corpora, with a range of parameters. ER -
KILGARRIFF, Adam, Pavel RYCHLÝ, Miloš JAKUBÍČEK, Vojtěch KOVÁŘ, Vít BAISA a Lucia KOCINCOVÁ. Extrinsic Corpus Evaluation with a Collocation Dictionary Task. Online. In Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Hrafn Loftsson and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis. \textit{Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)}. Reykjavik, Iceland: European Language Resources Association (ELRA), 2014, s.~1-8. ISBN~978-2-9517408-8-4.
|