Benchmarking natural-language parsers for biological applications using dependency graphs Andrew Clegg and Adrian J Shepherd |
BLLIP (Charniak-Johnson-Lease parser) github repository |
BLLIP reranking parser (also known as Charniak-Johnson parser, Charniak parser, Brown reranking parser) - The latest version is available at GitHub.
|
BUBS Parser - a grammar-agnostic constituent parser, designed and tuned for efficient context-free inference. Using a high-accuracy grammar (such as the Berkeley latent-variable grammar), it achieves high accuracy and throughput.
|
C&C CCG parser |
Charniak-Lease (PCFG) parser - This version was trained on BIO-data (only POS-tagger was retrained) and achieved an F-score of around 0.8.
|
Combinatory Categorial Grammar (CCG) parser |
DeSR - multilingual dependency parser
|
DKPRO a set of useful open-source UIMA components |
FreeLing - A comprehensive toolkit that includes tokenization, morphology, POS tagging, NER, and dependency parsing modules for various languages.
|
Google's SyntaxNet: Parsey McParseface in 40 languages |
Graph & Transition based dependency parsers using BiLSTM feature extractors. |
Link Grammar |
LTAG-spinal |
MaltParser |
MBSP for Python |
Michael Collins' parser - (written as a PhD project)
|
MiniPar - Dependency parser.
|
MstParser |
Multilingual statistical parsing engine |
Neural CRF Parser |
NLP4j - NLP tools from Emory university (a former ClearNLP and ClearParser)
|
OpenNLP - The Apache OpenNLP library is a machine learning based toolkit for the processing of natural language text.
|
Pro3Gres: PRObability-based, PROlog-implemented Parser for RObust Grammatical Relation Extraction System Gerold Schneider |
Puck - a high-speed, high-accuracy parser for natural languages using GPU. It's (currently) designed for use with grammars trained with the Berkeley Parser and on NVIDIA cards. On a mid-range Nvidia GTX 680, it can parse over 400 sentences a second, or over half a million words per minute.
|
redshift - a very fast dependency parser (up to 1000 sentences per second).
|
Self-trained biomedical parsing (a modification of the Charniak parser) - A very effective bio-medical parser with an F-score close to 0.9
|
SENNA - Semantic Role Labeling (PropBank style), part of speech (POS) tagging, chunking, named entity recognition, syntactic parsing.
|
SharpNLP - a collection of natural language processing tools written in C#.
|
spaCy - A fast but accurate POS tagger and dependency parser.
|
Stanford Parser |
SyntaxNet - Neural Models of Syntax: release includes all the code needed to train new SyntaxNet models on your own data, as well as an accurate Parsey McParseface.
|
The AOT parser - The Syntactic/Dependency parser for Russian and German (there is also support for morphology).
|
YARA parser - a fast (up to 4000K sentences per second) dependency parser.
|