Language analysis technologies

Software and knowledge bases for linguistic processing

CELI provides software components and linguistic resources that can be used for various purposes: the "building blocks" to construct systems that include linguistic intelligence.
CELI consultants will provide advice on the best choice of modules and resources for your project; depending on requirements, technical needs and preferred licensing conditions, one can choose from a set of pre-packaged resources or opt for a personalized solution.

Demos of some of the available language resources are available here.

Linguistic knowledge bases

textual corpora for the study, training and evaluation of NLP systems
generic corpora by language, for the following languages: Italian, English, French, Spanish, Catalan, Portuguese, German, Dutch, Swedish, Norwegian, Finnish, Danish, Polish, Russian, Estonian, Latvian, Lithuanian, Ukrainian, Greek, Turkish, Arabic, Hebrew, Armenian, Albanian, Croatian, Serbian, Czech, Slovak, Slovenian, Romanian, Bulgarian, Hungarian, Chinese, Japanese
domain-specific corpora, in other words, collections of texts regarding specific topics: automotive, food, cosmetics, fashion, telecommunication, public administration...
specialized morphological lexica:
the base-modules of morphological analysis are provided with a generic lexicon of broad coverage for a specific language; for more specific applications, CELI offers specialized lexica for the analysis of texts dealing with specific topics.
lexica and semantic networks: multilingual, generic, and domain specific (legal terminology, medical terminology, automotive terminology...)

Software modules

modules for the morphological analysis of the following languages: Italian, English, French, Spanish, Catalan, Portuguese, German, Dutch, Swedish, Norwegian, Finnish, Danish, Polish, Russian, Belarusian, Estonian, Latvian, Lithuanian, Ukrainian, Greek, Turkish, Arabic, Hebrew, Armenian, Albanian, Croatian, Serbian, Czech, Slovak, Slovenian, Romanian, Bulgarian, Hungarian, Japanese
modules for statistical classification, based on application-specific training
modules for rule-based syntactic/semantic analysis; analytical rules can be personalized for specific applications
modules for information extraction based on syntactic/semantic analysis
hybrid symbolic/statistical analysis systems, for the best balance between precision and robustness in contexts with broad linguistic variability
modules for question-answering
recognition of opinions and sentiments expressed on topics or objects (products, brands...)
modules for the automatic recognition of notable entities (proper nouns, places...etc.)
language detection for a written language
tools for designing text-to-speech systems (phonetic transcription)

Language analysis technologies

Software and knowledge bases for linguistic processing

Linguistic knowledge bases

Software modules

To find out more