erosenfeld / Thesaurus
A dynamically generated thesaurus using Syntactic N-grams parsed by Google Research. Rather than providing synonyms, this thesaurus provides words used in similar contexts. It also provides actual values, so certainty of similarity can be properly gauged.
☆16Updated 11 years ago
Related projects ⓘ
Alternatives and complementary repositories for Thesaurus
- A tool for calculation semantic similarity between words from a text corpus based on lexico-syntactic patterns.☆28Updated 8 years ago
- Performs multi document summarization. Includes a method to generate summaries: The method uses a sentence importance score calculator ba…☆37Updated 11 years ago
- Solrstrap is a Query-Result interface for Solr written in JavaScript, HTML and CSS☆86Updated 7 years ago
- One trick pony NLP library for extracting keywords from HTML documents☆18Updated 8 years ago
- The Community-enRiched Open WordNet (CROWN)☆19Updated 8 years ago
- Machine translation for the real world☆23Updated 4 years ago
- Algorithmic summarizer for RSS/Atom Feeds, Web Urls and arbitrary text. Codebase for the application deployed at http://tldrzr.herokuapp.…☆53Updated 8 years ago
- ☆42Updated 8 years ago
- Client for Stanford Named Entity Reconginiton☆27Updated 6 years ago
- A Javascript Implementation of the Porter Stemmer☆96Updated 3 years ago
- Node wrapper for Ark-TweetNLP.☆16Updated 9 years ago
- Linking Entities in CommonCrawl Dataset onto Wikipedia Concepts☆59Updated 12 years ago
- English Dependency Relationship Extractor☆85Updated 11 months ago
- The SRL-based Open IE extractor. A principal component of Open IE 4.0.☆19Updated 7 years ago
- Analysis plugin for ElasticSearch providing capability for processing inline annotations in documents.☆35Updated 10 years ago
- A parts-of-speech chunker.☆30Updated 9 years ago
- FacetView is a pure javascript frontend for ElasticSearch.☆291Updated 9 years ago
- Shell scripts to assist downloading & processing the Google n-grams corpora☆14Updated 7 years ago
- http://www.ark.cs.cmu.edu/ARKref/☆32Updated 10 years ago
- Server endpoint for communicating with stanford-ner server☆25Updated 6 years ago
- DKPro WSD: A Java framework for word sense disambiguation☆20Updated 2 years ago
- A semi-unsupervised language independent morphological analyzer useful for stemming unknown language text, or getting a rough estimate of…☆21Updated 6 years ago
- Information Extraction System can perform NLP tasks like Named Entity Recognition, Sentence Simplification, Relation Extraction etc.☆27Updated 10 years ago
- SKOS analysis for Elasticsearch☆54Updated 8 years ago
- js utility for summarizing large bodies of text using a basic sentence relevance ranking algorithm☆101Updated 8 years ago
- Stanford Pattern-based Information Extraction and Diagnostics -- Visualization☆94Updated 10 years ago
- A web service that computes a set of readability metrics for text. We currently support the following metrics: Automated Readability Inde…☆71Updated 2 years ago
- Nodejs text sumarization☆55Updated 10 years ago
- NodeJS Named Entity Recognition, using Stanford NER (easy install)☆40Updated 7 years ago