website for the SFU natural language lab
A General Purpose Tagger for POS Tagging, NER Tagging, and Chunking.
Tree-adjoining grammar based statistical dependency parser using a general linear model (glm).
This is the implementation of word aligner using Hidden Markov Model
Lensing Wikipedia is an interface to visually browse through human history as represented in Wikipedia. This the source code that runs the website:
Website for the TAG+9 workshop.
Left to right decoding for Hiero Statistical Machine Translation
The XTAG English Grammar mirrored from the XTAG page http://www.cis.upenn.edu/~xtag/
website for the North West NLP conference 2014
Metaphor dataset: literal versus non-literal uses of words
use typed alignment links to improve word alignment
Code for multi-lingual alignment using HMMs
Constrain HMM with graph propagation
Decipherment by marching crib text across to solve (simple) substitution ciphers.
Visualize bilingual word embeddings.
Python code for phrase extraction and different types of SCFG rule extraction from word aligned parallel data.
Graph propagation for statistical machine translation
Python module for working with the Penn Treebank
Hierarchical phrase-based machine translation system
This repository provides codes required for testing hadoop functionality.
Python code to read, display and parse with the XTAG English (and other) grammars as part of the NLTK project.
Use Vickrey-Koller simplification rules for semantic role labeling
Korean grammar in the Tree Adjoining Grammar framework developed as part of the XTAG project at UPenn.
Moses, the machine translation system
Alignment with word segmentation (e.g. Chinese-English) or morph segmentation (e.g. Korean-English)
Implementation of the Yarowsky algorithm and other bootstrapping algorithms.