RelEx Dependency Relationship Extractor

Link: https://launchpad.net/relex/

Documentation: http://wiki.opencog.org/w/RelEx

RelEx is an English-language dependency relationship extractor, built on the Carnegie-Mellon link parser. It can identify subject, object, indirect object and many other dependency relationships between words in a sentence. It also generates some advanced semantic relations, such as normalizing questions for question-answering. It also proposes "frames" or "semantic roles", similar in style to those of FrameNet. RelEx includes a basic implementation of the Hobbs anaphora (pronoun) resolution algorithm. As a "by-product", it also provides more basic functions, including entity detection, part-of-speech tagging, noun-number tagging, verb tense tagging, gender tagging, and so on. Relex now includes a Stanford parser compatibility mode, generating identical output, but more accurately and more quickly.

Alignment Set Toolkit

http://gps-tsc.upc.es/veu/personal/lambert/software/AlignmentSet.html

Training SMT incrementally

For word alignments

Force Alignment: http://geek.kyloo.net/software/doku.php/mgiza:forcealignment

MGIZA++: http://geek.kyloo.net/software/doku.php/mgiza:overview and http://sourceforge.net/projects/mgizapp/

For translation models

Stream-based Translation Models for Statistical Machine Translation

Abby Levenberg, Chris Callison-Burch and Miles Osborne, NAACL 2010.

For language models

Stream-based Randomised Language Models for SMT

Abby Levenberg and Miles Osborne, EMNLP 2009.

Discourse Parsing

Sentence-based level:
SPADE: http://www.isi.edu/licensed-sw/spade/

Text-base level:
HILDA: http://nlp.prendingerlab.net/hilda/
NUS demo: http://wing.comp.nus.edu.sg/~linzihen/parser/demo.html

(to be continued!)

Open source toolkits for cloud computing

Eucalyptus: http://www.eucalyptus.com/

OpenNebula: http://www.opennebula.org/doku.php

[Book] - Foundations of Computer Science

http://infolab.stanford.edu/~ullman/focs.html

(VNese fresh CS students should consider reading this book!)

Scientext corpus

http://scientext.msh-alpes.fr

Scientext is a new, on-line French and English corpus of scientific texts. The corpus includes 4.8 million running tokens in French, 13 million words of research articles in English (medicine and biology), and an English-language sub-corpus of French undergraduate students’ texts (1,1 million words). The corpus is organized to facilitate the linguistic study of authorial position and reasoning in scientific articles through phraseology and lexico-grammatical markers linked to causality.