Thinknowlogy is grammar-based software designed to utilize the logic contained within grammar in order to create intelligence through a natural language, which is demonstrated by programming in a natural language, reasoning in a natural language (drawing conclusions, making assumptions (with a self-adjusting level of uncertainty), asking questions (about gaps in the knowledge), and detecting conflicts), and intelligent answering of "is" questions, providing alternative answers as well.
Bitextor is an application whose objective is to generate translation memories using multilingual Web sites as a corpus source. It downloads all the HTML files in a Web site, it performs a preprocess to convert them to a coherent and suitable format and, finally, applies a set of heuristics (based mainly on HTML tag structure and text block length) to make pairs of files which are candidates to contain the same text in different languages. From these candidates, translation memories are generated in TMX format using the library LibTagAligner, which uses the HTML tags and the length of text chunks to perform the alignment.
TagAligner is an application whose objective is to generate translation memories from two XHTML tagged files. It uses XHTML tag structure and text block length to calculate the most probable alignment between the both files. Once it has done so, TagAligner uses a set of rules defined by the user to cut every text block into phrases and then it generates a TMX file that represents the translation memory obtained from the original files. You can download TagAligner as an application or as a library to be used by other applications.
RelEx is an English-language semantic dependency relationship extractor, built on the Carnegie-Mellon Link Grammar parser. It can identify subject, object, indirect object, and many other syntactic dependency relationships between words in a sentence; it generates dependency trees, resembling those of dependency grammars, and specifically, those of Dekang Lin's MiniPar and the Stanford parser. It accomplishes this by applying a sequence of rules, based on the local context, and thus resembles constraint grammar in its implementation. In this sense, it implements some of the ideas of Hudson's Word Grammar. However, unlike other dependency parsers, RelEx attempts a greater degree of semantic normalization.
The AlchemyAPI Android SDK enables real-time semantic analysis of text, HTML, or Internet-hosted Web page content. The SDK provides mechanisms to extract Concepts, Named Entities, Keywords and Tags, Categories, and clean HTML into text, and even detects languages. It can analyze text in eight different languages: English, French, German, Italian, Portuguese, Russian, Spanish, and Swedish. Example code and a demo application are included to help get you started.
Wintermute is an intelligent framework of applications and libraries that uses neural networking to learn about its host. A pseudo-langauge engine that permits translations and grammar rulesets of any language to be incorporated into the system, and database downloads of different sets of data combine to provide a virtual self-thinking assistant that can be used to perform tasks like dictation to a text editor, and more complex tasks such as sorting of documents depending on the time of day, or automation of other routine tasks. It should be noted that Wintermute itself is a meta-project. It encompasses a large array of currently existing and potential produced projects.
jWeb1T is an Java tool for efficiently searching n-gram data in the Web 1T 5-gram corpus format. It is based on a binary search algorithm that finds the n-grams and returns their frequency counts in logarithmic time. As the corpus is stored in many files, a simple index is used to retrieve the files containing the n-grams.