IXA is a research group working, on the natural language processing at the University of the Basque Country , It is a multidisciplinary group composed of 42 computer scientists and 12 linguists.
We work together on algorithms, tools and linguistic resources that allow computers to process and understand human languages, especially Basque. Our work ranges from basic research in computational linguistics to key applications in human language technology, and covers areas such as Information Retrieval and Information Extraction, Machine Translation, Language learning, Morphology, Syntax-Morphosyntax, Lexicography-Semantics, Basic facilities and Integrations of Language Tools (SGML, XML).
Two distinguishing features of the Ixa Group are mainly that we deal with a less resourced language (Basque) and that we combine linguistic modelling and data analysis with innovative probabilistic and machine learning approaches to NLP. Those characteristics lead us to face Language Technology with a characteristic strategy.
Basque is the ancestral language of the Basque people. It is likely that an early form of the Basque language was already present in Western Europe before the arrival of the Indo-European languages. Nowadays, Basque is a minority language with very different linguistic features compared to its main neighbouring languages (Spanish, French or English). It is an agglutinative language, with a rich inflectional morphology; for example each adjective may tackes,at least 360 word forms.
Our research has resulted in state-of-the-art technology for robust, broad-coverage natural-language processing for Basque. These technologies include a spelling checker (Xuxen), a machine translation system (OpenTrad), Basque wordnet (BasWN), the corpus of Science and Technology (ZT corpus) and a syntactically annotated corpus (EPEC). For information about more resources, tools and applications see the products page.
The Ixa Group is a multidisciplinary team that includes members of five departments in the University of the Basque Country: Computer Languages and Systems, Computer Architeture and Technolgy, Basque Filology, Computation Sciences and Artificial Intelligence and Didactic of Language and Literature.