Abstract— Monolingual text-to-text generation is an emerging research area in Natural Language Processing. One reason for the interest in such generation systems is the possibili...
When implementing computational lexicons it is important to keep in mind the texts that a NLP system must deal with. Words relate to each other in many different, often queer, way...
Roberto Basili, Maria Teresa Pazienza, Paola Velar...
This paper presents a methodology for automatic learning of ontologies from Thai text corpora, by extraction of terms and relations. A shallow parser is used to chunk texts on whic...
Statistical machine translation (SMT) requires a large parallel corpus, which is available only for restricted language pairs and domains. To expand the language pairs and domains...
We combine two complementary ideas for learning supertaggers from highly ambiguous lexicons: grammar-informed tag transitions and models minimized via integer programming. Each st...