This paper addresses the representation of the main elements of instructional models using formal ontology languages. Following existing conceptualizations, models, methods and con...
In this paper we introduce a statistical Named Entity recognizer (NER) system for the Hungarian language. We examined three methods for identifying and disambiguating proper nouns...
We present a method for learning bilingual translation lexicons from monolingual corpora. Word types in each language are characterized by purely monolingual features, such as con...
Aria Haghighi, Percy Liang, Taylor Berg-Kirkpatric...
Many existing methods for bilingual lexicon learning from comparable corpora are based on similarity of context vectors. These methods suffer from noisy vectors that greatly affec...
We develop a new approach to learning phrase translations from parallel corpora, and show that it performs with very high coverage and accuracy in choosing French translations of ...