Developed at the
University of Lisbon, Dept. of Informatics, by the
NLX-Natural Language and Speech Group.
features
|
versão portuguesa
Features
Table of contents
LX-Inflector
LX-Inflector (beta version) is a freely available online service for the
nominal lemmatization and inflection of Portuguese. It was developed and is mantained by the
NLX-Natural Language and Speech Group at the
University of Lisbon,
Department of Informatics.
Features
At the date of its inception, LX-Inflector is the first freely available online service
for fully-fledged Portuguese nominal inflection and lemmatization.
It takes as input:
- A Portuguese nominal form
A forms of a noun or an adjective, including adjectival forms of past
participles, and
- Inflectional feature values
Intended values of inflectional features of Gender and Number for the output.
It delivers:
- Inflectional features
The input form is returned with the corresponding values for the inflectional
features of Gender and Number associated to it;
- Lemmata
The lemmata (singular and masculine forms when available) possibly
corresponding to the input form;
- Inflected forms
The inflected forms (when available) of each lemmata in accordance with the
values for inflectional features entered.
LX-Inflector processes simple forms, both lexically known and unknown ones.
It also processes compound forms. It handles nominal forms with prefixes as well.
In sum, it lemmatizes and inflects:
- Prefixed forms
Nominal expressions integrating one or more prefixes, e.g.
"anti-constitucional", "super-mega-fixe", etc;
- Compounds
Nominal expressions integrating more than one form, e.g.
"trabalhador-estudante", "surdo-mudo", "lança-mísseis", etc;
- Neologisms
By activating the force inflection option, the input form is processed by forcing the application of regular inflection, however the appropriate output form is regular, irregular or non-existent.
N.B.: Every form is processed by the inflector, being up to the user to ensure its correct categorization (as Noun or as Adjective) as well as its orthographical correctness. In case the input form is mispelled, that input is taken as a neologism by the inflector.
Authorship
LX-Inflector is being developed by
António Branco and
Pedro Martins, with the help of João Silva, and the contribution of Catarina Ribeiro and Ricardo Santos of the
NLX-Natural Language and Speech Group, at the
University of Lisbon,
Department of Informatics.
Acknowledgments
The work leading to the LX-Inflector was partly supported by FCT-Fundação
para a Ciência e Tecnologia under the grant POSI/PLP/47058/2002 for the project TagShare.
Contact us
Contact us using the following email address: 'nlxgroup' concatenated with 'at'
concatenated with 'di.fc.ul.pt'.
Why LX-Inflector?
LX because LX is the "code" name Lisboners like to use to refer to their
hometown.