Discover Services

New components are added constantly, but as of September 2015, the wrapped components included Tokenizers (Stanford Tokenizer, GATE ANNIE Tokeniser, OpenNLP Tokenizer), Taggers (Stanford Tagger, GATE Part of Speech Tagger, OpenNLP POSTagger), Sentence Splitters (Stanford Sentence Splitter, GATE Sentence Splitter, OpenNLP Splitter), Named Entity Recognizers (Stanford Named Entity Recognizer, GATE Named Entity Recognizer, OpenNLP NamedEntityRecognizer), Parsers (Stanford Phrase Structure and Dependency Parser, OpenNLP Parser), Chunkers (GATE Noun Phrase Chunker, GATE Verb Phrase Chunker), the GATE Gazetteer and the GATE OrthoMatcher. In addition, there are various converters between popular formats (UIMA/CAS, GATE, LIF) and services to give access to MASC data and LDC Gigaword data. Finally, there are several services that aid in evaluation, including the OAQA evaluation service at CMU and a component to compares annotations in two documents.

All services hosted at the Vassar and Brandeis LAPPS servers are listed at http://grid.anc.org:8080/service_manager/language-services and http://eldrad.cs-i.brandeis.edu:8080/service_manager/language-services.

A discovery tool to find services based on their input and output requirements is under development.