Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1210679, author = {Baisa, Vít}, address = {Brno}, booktitle = {Eighth Workshop on Recent Advances in Slavonic Natural Language Processing}, keywords = {language model; suffix array; LCP; trie; character-based; random text generator; corpus}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, pages = {3-10}, publisher = {Tribun EU}, title = {Character-based Language Model}, url = {https://nlp.fi.muni.cz/raslan/2014/6.pdf}, year = {2014} }
TY - JOUR ID - 1210679 AU - Baisa, Vít PY - 2014 TI - Character-based Language Model PB - Tribun EU CY - Brno KW - language model KW - suffix array KW - LCP KW - trie KW - character-based KW - random text generator KW - corpus UR - https://nlp.fi.muni.cz/raslan/2014/6.pdf N2 - Language modelling and also other natural language processing tasks are usually based on words. I present here a more general yet simpler approach to language modelling using much smaller units of text data: character-based language model (CBLM). In this paper I describe the underlying data structure of the model, evaluate the model using standard measures (entropy, perplexity). As a proof-of-concept and an extrinsic evaluation I present also a random sentence generator based on this model. ER -
BAISA, Vít. Character-based Language Model. In \textit{Eighth Workshop on Recent Advances in Slavonic Natural Language Processing}. Brno: Tribun EU, 2014, p.~3-10. ISSN~2336-4289.
|