Convidar Freelancer para Projeto
Parece que você não tem um projeto ativo no momento. Por que não postar um projeto agora? É grátis!Publique um Projeto
- 75%Trabalhos concluídos
- 100%No Orçamento
- 25%Taxa de Recontratação
Tokenizing, Tagging and Lemmatizing free running texts (TTL)código
Dependency linking (LexPar)código
Mining for parallel sentences in comparable corpora (LEXACC)código
Project for raduion
“Excellent job once again.”slipp Mar 6, 2007
“Radu is an excellent programmer. His coding is lean and clean. During the project he came up with his own ideas to make the tool even better than I imagined in the first place. Excellent communication, reliable and straightforward.”slipp Mar 6, 2007
Parse and write file scrape
“This guy is very good, he communicates well, and his Perl coding isvery good. He asks clear questions and delivers fast.”comfortfeet Jan 25, 2007
Senior ResearcherAug 2001
I am a Natural Language Processing researcher. I currently work on/with: - machine translation (e.g. Moses) - part-of-speech tagging (e.g. HMMs, neural nets) - lemmatization/stemming - word sense disambiguation - parsing (syntactic analysis, dependency parsing) - question answering - word alignment - automatic bilingual dictionary extraction from parallel or comparable corpora Full resume can be found here: [login to view URL]~radu/
Junior C++ ProgrammerJan 2001 - Mar 2001 (2 months)
C++ programming in the company's COSWIN application.
Bachelor of Engineering in Computer Science1996 - 2001 (5 years)
Graduate Studies in Computer Science2001 - 2002 (1 year)
Master in Theoretical Lingustics2002 - 2003 (1 year)
PhD in Computer Science/Natural Language Processing2003 - 2007 (4 years)
Wikipedia as an SMT Training Corpus
We have mined for parallel sentences in the Wikipedia seen as a comparable corpora. We have tested the quality of the corpus by doing SMT with Moses trained on the extracted data.
The Romanian wordnet in a nutshell
This is an account of the current development activities of the Romanian semantic network, aligned to Princeton WordNet.
Large tagset labeling using Feed Forward Neural Networks. Case study on Romanian Language
High accuracy POS tagging with neural nets, using a large tagset named Morpho-Syntactic Descriptors.
Conectado com o Facebook
- Telefone Verificado
- E-mail Verificado