An intelligent search engine for MEDLINE

Retrieve abstracts or sentences in MEDLINE using deep-parsing results.


A GUI-based efficient MEDLINE search tool

List the proteins or genes which interact with the given protein or gene.


GENIA Corpus

A collection of annotated abstracts taken from MEDLINE database.

Technical terms, parts-of-speech, and syntactic trees are annotated. TEI version of GENIA corpus version 3.0 (Dr. Tomaz Erjavec, Jozef Stefan Institute, Slovenia).

NLP Tools


A deep syntactic parser for English

Output phrase structures and predicate argument dependencies. High parsing speed (more than 20 sentences per second) and high accuracy (88-90% accuracy of predicate argument dependencies).


A shift-reduce dependency parser

A shift-reduce dependency parser that uses maximum entropy models for scoring parser actions and a best-first strategy to search for the best parse.

GENIA Tagger

Part-of-speech tagging and shallow parsing for biomedical texts

Specifically tuned for biomedical texts. POS tagging accuracy of 97-98%. Shallow parsing accuracy of 91-94%.

GENIA Sentence Splitter

A sentence splitter for biomedical texts

Optimized for biomedical texts. The classifier achieved an F-score of 99.7 on 200 unseen GENIA abstracts.

Machine Learning


A maximum entropy estimator for feature forests.

Parameter estimation algorithm for feature forests. Support GIS, IIS, and limited-memory BFGS

Maxent Classifier

A simple C++ library for maximum entropy classifiers

Fast parameter estimation using the BLMVM algorithm. Modelling with inequality constraints.

Programming Language


A logic programming language for typed feature structures.

A logic programming language similar to Prolog. Manipulation of feature structures as builtin data structure. High-speed runtime system. C++ library support for feature structures.

Development Tools


A GUI client for browsing feature structures

Intended to work with LiLFeS.


A grammar converter from LTAG to HPSG

The conversion guarantees strong equivalence of grammar.