CogcompNLP

I am working with CogCormp, the University of Illinois' premier Natural Language Processing team, as an undergraduate researcher; I am currently building a pipeline that can interact with a server to return tokenized output of natural language.

The details of the work this team has done is below:

This project collects a number of core libraries for Natural Language Processing (NLP) developed by the University of Illinois' Cognitive Computation Group.

CogComp's main NLP libraries

Each library contains detailed readme and instructions on how to use it. In addition the javadoc of the whole project is available here.

Module Description
illinois-nlp-pipeline Provides an end-to-end NLP processing application that runs a variety of NLP tools on input text.
illinois-core-utilities Provides a set of NLP-friendly data structures and a number of NLP-related utilities that support writing NLP applications, running experiments, etc.
illinois-corpusreaders Provides classes to read documents from corpora into illinois-core-utilities data structures.
illinois-curator Supports use of Illinois' NLP Curator, a tool to run NLP applications as services.
illinois-edison A library for feature extraction from illinois-core-utilities data structures.
illinois-lemmatizer An application that uses WordNet and simple rules to find the root forms of words in plain text.
illinois-tokenizer An application that identifies sentence and word boundaries in plain text.
illinois-pos An application that identifies the part of speech (e.g. verb + tense, noun + number) of each word in plain text.
illinois-ner An application that identifies named entities in plain text according to two different sets of categories.
illinois-quantifier This tool detects mentions of quantities in the text, as well as normalizes it to a standard form.
illinois-inference A suite of unified wrappers to a set optimization libraries, as well as some basic approximate solvers.

Built With

Share this project:

Updates