Search Results for "artificial intelligence projects in java" - Page 3

Task of the project is a semantic annotation of Czech texts by using NLP tools.

Basic natural language processor capable of solving elementary math word problems such as: 1) John has 7 pencils. He buys 10 more pencils. How many pencils does he have in all? 2) There are 6 boys and 4 girls in a library. How many kids are there altogether? 3) Bob ran 8 miles and Stella ran 2 miles. How many miles did they run altogether? 4) What is the sum of 7 and 2? 5) What is 8 divided by 2? 6) What is the 10 subtracted by 2? 7) What is 2 subtracted from 10? Also shows users...

Code for syntactic parsing and other natural language processing applications.

G-Asks is a question generation system, developed by LATTE(Learning and Affect Technologies Engineering) research group at The University of Sydney. It uses Natural Language Processing techniques and Machine learning algorithms to generate specific trigger questions. If you use this software in a publication, please cite the paper 2. 1.Ming Liu and Rafael A. Calvo (2012) “Using Information Extraction to Generate Trigger Question for Academic Writing Support”, 11th International Conference...

Multi-agent Development Environment for Natural Language Processing Java Based System Development framework

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.

A multi-agent architecture for building interactive dramas. It uses the Jason's BDI engine, being the Jason's agent-oriented programming language utilized for performing the drama management and for authoring behaviors for the characters.

This is a Java-based project for complex event extraction from text and co-reference resolution. Currently the code can read BioNLP shared task format (http://2011.bionlp-st.org/) and i2b2 Natural Language Processing for Clinical Data shared task format (https://www.i2b2.org/NLP/DataSets/Main.php). Event extraction includes finding events and the parameters for an event in a text. The method is based on SVM but other ML algorithms can be adopted. The method details are explained in the...

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.

This application illustrates natural language processing using tagged grammars and statistical classification. Outputs are shown with the EMMA specification of the W3C. A viewer is provided to allow for more user-friendly viewing of EMMA results.

Web application to make user-friendly requests on large XML database. Tools to XML-ize large bodies of semi-formal texts (like floras). Computer-assisted specimen identification. Uses natural language processing, 2D/3D images analysis and generation.

Natural language processing projects.

Clipsyll is a collection of scripts and programs for dowloading, codifying, analysing (using NLTK) CLIPS, the largest Italian corpus of spoken language. It includes a syllabification module based on the SSP: http://sourceforge.net/projects/silly

Reconcile is an open source research platform for coreference resolution. It combines a large number of open source NLP components and provides extension points for researchers to plug in additional features and techniques.

Maximum entropy is a powerful method for constructing statistical models of classification tasks, such as part of speech tagging in Natural Language Processing. Several example applications using maxent can be found in the OpenNLP Tools Library.

A language modeling tool kit written in Java for natural language processing applications. It can handle character-by-character modeling of unknown words, language model combination, comparison, and evaluation, as well as a number of smoothing techniques

Java Suffix array library for phrase discovery. Inspired initially by the classic paper of Yamamoto & Church, with newer ideas from Abouelhoda et al and Kim et al. Adapted for large alphabet so that words can be tokenized as alphabet characters.

This project is contains implementations of algorithms to integrate the output of different NLP tools (part of speech taggers, morphologies, parsers, etc.) in order to obtain more accurate, more robust and more fine-grained linguistic analyses. Note that the code is outdated, but left here for documentation purposes. Its functionality may be reimplemented within the NLP2RDF project (http://code.google.com/p/nlp2rdf).

NLP using java and related technologies.

D.U.C.K (Determine segmentation of Unknown words by using Context Knowledge)is an NLP tool, which aims to find the correct segmentation for unknown words in written Hebrew. Statistics from different scopes will be used to determine the segmentation.

Sanchay is a collection of tools and APIs for language researchers. It has some implementations of NLP algorithms, some flexible APIs, several user friendly annotation interfaces and Sanchay Query Language for language resources.

This project is a compilation of tools/libraries to help with tasks related to Text Analytics mainly in Java. These tools range from simple wrappers to sophisticated mining tasks that can improve the productivity of researchers and engineers.

OpenDMAP (Open Source Direct Memory Access Parser) is a natural language processing (text mining) application: a semantic parser for information extraction.

NLP4J library is a toolset written in Java for Natural Language Processing. This version is oriented to Document Classification and uses Naive Bayes, TF-IDF, etc. There are also pre-processing tools.

a natural language processing engine to allow Apache Lucene to process text