Connexor Machinese

Machinese is a suite of well-supported software components and practical solutions to normalize, categorize and extract concepts, names, facts and other text analytics from documents written for diverse audiences in many languages. Machinese products are designed to serve both volume- and knowledge-intensive applications. Applications related to search, data mining, indexing, document clustering and routing often need to process huge amounts of data. Connexor's Machinese libraries transform naturally occurring text into linguistically analysed structured data that makes more sense to knowledge-intensive applications, to the benefit of the information consumer/analyst.

Machinese Tokenizer

Machinese Tokenizer is a set of program components that performs basic text analysis tasks quickly. It splits raw text into understandable word units and provides the possible base forms and classes for words.

Machinese Phrase Tagger

Machinese Phrase Tagger is a set of program components that performs basic linguistic analysis tasks. It splits raw text into understandable word units and provides the possible base forms and classes for words.

Machinese Syntax

Machinese Syntax provides a full analysis of texts by showing how words and concepts relate to each other in sentences.

Machinese Metadata

Connexor Machinese Metadata is a high-performance text analytics and metadata automation solution, which extracts information in ten different languages.

Feature matrix

The table below explains which output features different Machinese analysers offer. Note that the table excludes Machinese Metadata, which uses totally different kind of output than other Machinese analysers as it only prints out entities and information about their occurrences rather than each and every token of the text.

	Machinese Tokenizer	Machinese Phrase Tagger	Machinese Syntax
Tokenisation	●	●	●
Morphological analysis		●	●
Base forms	●	●	●
Decompounding	●	●	●
Disambiguation		●	●
Phrasal analysis		●	●
Name tagging		●
Syntactic structure			●

---

Glossary

As the above includes some terms not necessarily known to all readers, glossary provides explanations for the key terms relating to Connexor technologies.