Search Results for "artificial intelligence java source code"

memfree is an open source hybrid AI search engine and page generation platform designed to help users retrieve information from both personal knowledge bases and the public web through a unified interface. The project combines retrieval-augmented search with AI summarization to deliver concise answers instead of forcing users to manually sift through multiple sources. It supports multiple AI models and search providers, enabling flexible configuration depending on cost, performance, or...

Project moved to GitHub! https://github.com/carrot2/carrot2 Carrot2 is an Open Source Search Results Clustering Engine. It can automatically organize small collections of documents, e.g. search results, into thematic categories. Carrot2 integrates very well with both Open Source and proprietary search engines.

This package contains different tools to add NLP capabilities for Lucene 4.x (it has been tested using Lucene version from 4.6.x to 4.8.1). Although it was originally developed for German, it is, mostly, language independent. It allows the user to lemmatize words to be indexed, to weight termy ba their parts of speech (e.g. weighting nouns mor hevaily than pronouns), and to add synonyms taken from GermaNet or a list you provide to the search index and thereby increase recall of lucene.

This project aims to build a suite of Natural Language Processing tools. Modules will include corpus indexing and access tools, a part-of-speech tagger, tokenisers, text classification software, etc.

TestEl is a Java-based learning analyzer for HTML (and possibly other) structured documents. It can be trained to detect structures in such documents and renders hits in XML.

This project provides cross-forge semantic search for the Qualipso Forge. It integrates A4 AdvDoc prototype (semantic search GUI and engine) with A3 homogeneous and heterogeneous cross-forge semantic search capabilities. See Qualipso.org for details

The Wikipedia Miner toolkit provides simplified access to Wikipedia. This open encyclopedia represents a vast, constantly evolving multilingual database of concepts and semantic relations; a promising resource for nlp and related research.

True-Hybrid Web Search Engine, which is designed to organize a web-based information by making heavy use of a mutually beneficial collaboration between Human and Artificial Intelligence.

A library to support spread activation techniques over ontologies.

Web-as-corpus tools in Java. * Simple Crawler (and also integration with Nutch and Heritrix) * HTML cleaner to remove boiler plate code * Language recognition * Corpus builder

The implementation of Bee Hive @ Work algorithm that simulates the foraging behavior of honey bees in nature. The aim is to provide an extensible framework that can be used by researchers to simply create new applications of this algorithm.

This project tries to find geographical locations (formulated by GPS positions) for specific queries (eg 'art') in specific environments (eg 'Maastricht') by analyzing webpages.

S3B - Social Semantic Search and Browsing - is a middleware that delivers a set of search and browsing components that can be used in J2EE web applications to deliver user-oriented features based on semantic descriptions and social networking

SYRAH si propone di far emergere e rappresentare i concetti espressi per mezzo di un linguaggio naturale. SYRAH aims to discover and represent concepts expressed in natural languages. NLP, lemma, lemmario, italiano, rete, semantica, clustering, semantic

DOSE: a distributed platform for semantic elaboration that provides semantic services such as automatic annotation of web resources at the document substructure level, semantic search facilities, semantic annotation storage and retrieval.

Open Source Semantic Web Search Engine Software: If two machines anywhere on the web can agree on the same definition of a digital service or digital good, then machine to machine transactions can use this lingua franca to transact on the users behalf.

This project intends to create an indexing search engine, for knowledge management. The primary object is to apply an information retrieval core. And implement a knowledge data discovery theory such as data mining algorithm, text mining.

SENTENSA Knowledge Miner is a platform independent tool for searching any text. SENTENSA uses robust methods of indexing and searching text, leveraging on experience from more than 20 years of information retrieval.

Catalogo is a system for cataloguing resources on a web site. It allows semantic search of information on an intranet using metadata, RDF and ontology concepts. It provides a Catalog server (Java web applications) and a Catalog client (Firefox plug-in).

The Jorne project develops software and open standards for linking Lojban text with WWW and Semantic Web metadata (e.g. RDF/N3, RSS, XML). Lojban is an artificial spoken and written language based on predicate logic.

A web-based, automated search engine that responds to user feedback through the use of artificial intelligence.

A Distributed Web Search System bassed on current high level nerual network ai for the rating algorithum and search direction.

The OpenBorges project intends to provide an humble place to experiment, and debate, about what can be an open, distributed, adaptive and collaborative, semantic virtual library. Inspirations are: As we May Think, Library of Babel, and Weaving the web

IDEAL means Information DEALer. A System wich provides the news and articles which the user wants. Using Tomcat, Struts, Java, MySQL an AgentSystem, Clustering, TF/IDF, Document Parser and it is multi user able.

HORUS is a system for knowledge acquisition, hypothesis generation, inference and learning. It is an interactive, internet environment accessible to a diverse community of users (public-access or membership basis) - see also UMKAILASH project for more.