Apertium is a machine translation platform, initially aimed at related-language pairs, but recently expanded to deal with more divergent language pairs (such as English-Catalan). The platform provides a language-independent machine translation engine, tools to manage the linguistic data necessary to build a machine translation system for a given language pair, and linguistic data for a growing number of language pairs.
Algraeph is a tool for manual alignment of linguistic graphs, such as phrase structure trees or dependency structures, where each node corresponds to a subsequence of the analyzed input sentence. It allows you to express the similarity between two graphs by aligning their nodes and attaching relation labels to these alignments. Graphs are read from one or more graphbanks (or treebanks) in the GraphML or Alpino formats. Alignment relations are user-defined and are stored in a simple XML format, which can be used for further processing. The resulting parallel graph corpus is a useful data set for many tasks in computational linguistics and natural language processing.
Grammar Browser provides a simple-to-use graphical interface to the grammatical structure and relations of any text, as parsed by the Stanford Parser. It contains a grammatical relation editor to modify, import, and export grammatical relation definitions (tregex patterns and features).
Cypher is an AI program that generates the RDF graph and SPARQL query representations of plain language input, allowing users to speak plain language to update and query databases. With robust definition languages, Cypher's grammar and lexicon can quickly and easily be extended to process highly complex sentences and phrases of any natural language, and can cover any vocabulary. Equipped with Cypher, programmers can begin building next generation semantic Web applications that harness natural language.
OpenEphyra is a question answering (QA) system. It retrieves answers to natural language questions from the Web and other sources. OpenEphyra comes with implementations of algorithms that proved effective in Carnegie Mellon's Ephyra system, which participated in the TREC evaluations. It is platform independent and can be set up in just a few minutes. The goal of this project is to give researchers the opportunity to develop new QA techniques without worrying about the end-to-end system.
The XEVM is an XML processing engine. It's a multi-threaded, Pub/Sub environment for dynamic programming on an event-driven state machine with TCP communications, tight fault free memory management, powerful set algebra, and a magical database. It is 100% C++ (25,000 LOC), with a thin porting layer; there are implementations for POSIX (Mac/Linux) and Win32. The XEVM is for processing XEPL (the Xepl Engine Programming Language).
SenseClusters is a natural language processing package that allows you to cluster similar contexts or to identify clusters of related words. It supports its own native methods based on first and second order representations of context, and also supports Latent Semantic Analysis. It is fully unsupervised, and can automatically discover the optimal number of clusters in your text. SenseClusters is a complete system that takes users from preprocessing of raw text to providing clustered output.
Isobel is a framework to build complex information retrieval and analysis systems. Isobel can be functionally divided in two subsytems, Isobel Gatherer (the crawling and filtering subsystem) and Isobel Analyzer (the analysis subsystem). The two subsytems can also be used separately. Isobel Gatherer offers ready-to-use services like content fetching, scheduling, document format conversion, Hyperlink graph storage and analysis, content storage and indexing. A programmer may easily add new services. Isobel Analyzer uses the IBM UIMA architecture to reuse the analysis components developed for this architecture.