We think that a good text analysis infrastructure helps a lot with respect to many research areas. Sometimes it is even a necessity in order to derive qualitatively new or more precise knowledge from corpus data.
If for example the words of a corpus are annotated morphologically and related to their basic forms (lemmata) and maybe even classified in addition according to their semantic contribution, it may be possible to cluster individual cases, which as such may be statistically insignificant, to statistically ‘recognizable’ and significant classes of events. In this way, it may be possible for example to recognize collocations or selectonal restrictions of complements or other relations basing on linguistic abstraction which otherwise would be unrecognizable because of the variousness of cases due to morphological differentiation and/or size of semantic classes etc.
Tools
In order to ease research in computational linguistics, Lingenio provides a number of research prototypes. In particular tools are available for:
- Morphological tagging
- Lemmatizing
- Semantic classification of words in texts
- Dependency analysis
- Underspecified semantic analysis
- Pronoun resolution
- Machine translation
- Cross-language analysis
for the languages German, English, French and, with restrictions, for Spanish.
Modalities of use
Prerequisite for using a tool for free is non-commercial use. We make the tools available for universities and other research institutions, provided the research purpose is confirmed in a corresponding form as well as non-proliferation of the software and if no competition position is to be expected with respect to the interests of Lingenio.
Procedure
If you are interested in the offer, please contact us and describe the task that you want to use the software for. If the preconditions described above are fulfilled we draw up a n agreement of cooperation which adapts the general conditions of use to the specific purpose.
When required we offer adaptation of our research prototypes to your specific parameters, in order that the combination of functions that is at your disposal is the one that you need.
We do not expect any service in return except making reference to the tool or the tools used on the corresponding project web pages and in publications if results are mentioned which were made with the help of the Lingenio software. We are happy of course if we receive feedback about the experiences made with our tools or if deepening of the cooperation results from their use. A common commercial exploitation of results is not excluded and can be agreed if there is correspoding interest.