Linguakit API (formerly CilenisAPI) helps you to analyze and extract information from texts. Add language technology to your software in a few minutes using our cloud solution. We offer you technology based on years of research in Natural Language Processing in a very easy and scalable SaaS model trough a RESTful API.
Recognizes the language in which a text is written. This module can distinguish several languages using language models and morphological structures.
Tells you whether it thinks the text you enter expresses positive sentiment, negative sentiment, or if it's neutral. It also gives you a quantitative weight to know how intense is the sentiment. It is available for Spanish, English, and Portuguese.
Extracts the most relevant words from a text and ranks them according to their degree of relevance. This module is very useful for automatic tagging, text comparison, topic detection… It is available for Spanish, English, Galician, and Portuguese.
Extracts the most relevant multiword terms from a text and ranked according to their degree of internal cohesion, for example: “mortgage rates”, “house price”, “building societies”, “price war”. It is a similar module to keyword extractor, but it finds the terms and topics that need more than one word to be expressed. The use cases are quite similar and a combination of both offers a powerful keyword, term or topic extraction. It is available for Spanish, English, Galician, and Portuguese.
Extracts from a text Named Entities and classify them as persons, places, organizations, and miscelaneous. By combining a morphosintatic analysis and machine learning algorithms, this FreeLing module offers Named Entity Recognition (NER) and Named Entity Classification (NEC). It is available for Spanish, English, Galician, and Portuguese.
Splits a text into words and phrases, including ambiguous separators like dots and colons. You can use it to count word frequency, to create your own tag cloud from any text in any language, etc.
Analyzes a text with FreeLing by providing words with PoS tags (e.g., noun, verb, preposition…), morphological features (singular, masculine…), and their lemmas (canonical form). It is available for Spanish, English, Galician, and Portuguese.
Gives the syntactic struture of a text using a dependency-based parser: DepPattern. All words of a text are structured in binary relations (dependencies). The system provides different ways of showing the final analysis: triplets, columns… It is available for Spanish, English, Galician, and Portuguese.
Searches all the occurrences of a word (in any language) within a text. and align them surrounded by the context in which they occur.
Returns the inflection of a verb, even verbs that don't exist, using the rules to conjugate it. This module is available for Galician, Spanish and Portuguese.