Multimedia annotation

how to split data in Perl

Ali Reza Ebadat — Wed, 18 Nov 2009 09:20:37 +0000

find some example of how to use “split”command in Perl here

Posted in programming Tagged: Perl

How to use GIZA++

Ali Reza Ebadat — Tue, 10 Nov 2009 17:02:11 +0000

GIZA++ is a program for aligning words and sequences of words in sentence aligned corpora. You can find more information about how to use it from following links:

http://kwang.blogdns.com/research/how-to-compile-install-run-giza.html/comment-page-1

http://wiki.apertium.org/wiki/Using_GIZA%2B%2B

Posted in Machine Translation Tagged: Machine Translation

Statistical Machine Translation Tutorial Reading

Ali Reza Ebadat — Tue, 10 Nov 2009 15:25:13 +0000

I have found a good tutorial about Statistical Machine Translation from Dr. David Kauchak webpage and I love NLP weblog.The second one is a copy of the first one.

The items listed are important to read for everyone who are interested to know about SMT.

Posted in Machine Translation Tagged: Machine Translation, Tutorial

How to build a Statistical Machine Translation very fast?

Ali Reza Ebadat — Tue, 10 Nov 2009 14:27:14 +0000

There is a guideline about how to use different toolkit to build aStatistical Machine Translation. You only need to have enough translation sentences in two languages.

By using

CMU Statistical Language Modelling Toolkit (version 2) for language model training
mkcls for training of word classes
GIZA++ for training of statistical translation models
ISI ReWrite Decoder (version 1.0.0a) for decoding (translation)
NIST MT evaluation kit (version 9) for BLEU and NIST evaluation

You can also use different tools like :

Pharaoh a decoder for phrase-based SMT
Rewrite a decoder for IBM Model 4

More detail about how to build Statistical Machine Translation

Pharaoh a decoder for phrase-based SMT
Rewrite a decoder for IBM Model 4

Posted in Machine Translation Tagged: Machine Translation

Another open source for CRF

Ali Reza Ebadat — Mon, 09 Nov 2009 10:04:23 +0000

Main web page : http://mallet.cs.umass.edu/

http://mallet.cs.umass.edu/sequences.php

Posted in Machine Learning Tagged: CRF, Machine Learning

Machine Learning summer school 2009 slides and videos

Ali Reza Ebadat — Fri, 06 Nov 2009 23:09:38 +0000

http://videolectures.net/mlss09uk_cambridge/

Posted in Machine Learning Tagged: Machine Learning, Summer School

SWIG

Ali Reza Ebadat — Tue, 27 Oct 2009 11:04:48 +0000

It is very useful to have an interface for your c/c++ program in different language programming like Perl, PHP, Python …

SWIG will do it very well. I didn’t know this software before working with a CRF tools written in C++. I have found different interfaces in different languages generated automatically by SWIG.

Posted in 1

Conditional Random Fields (CRFs)

Ali Reza Ebadat — Fri, 23 Oct 2009 14:03:14 +0000

Conditional Random Fields (CRFs) is a Machine Learning algorithm which could be consider as general form of HMM algorithm.

There is more information in in Wiki web page about Conditional Random Fields.

There is also a c++ implementation for CRF

Posted in 1

Semantic Annotation – comercial usage

Ali Reza Ebadat — Wed, 14 Oct 2009 12:57:53 +0000

In SEKT project they have built an ontology which could be useful for stock consult company to treat user requirement, giving good advise in real time …

There is a demo to show that how Sam can use a software which is built on this ontology to give good advise to the customers. This system will analyze emails, news, websites … to collect useful information related to users, companies and everything that could affect stock holders. So by using this system, Sam can give on time advise to customers who have special share to sell or give advise to buy something which could have a benefit for customer.

http://www.sekt-project.com/resources/demo/scene1.swf

Posted in Semantic Annotation

Controlled Natural Language

Ali Reza Ebadat — Mon, 05 Oct 2009 12:54:18 +0000

From Wikipedia:

“Controlled natural languages (CNLs) are subsets of natural languages, obtained by restricting the grammar and vocabulary in order to reduce or eliminate ambiguity and complexity. Traditionally, controlled languages fall into two major types: those that improve readability for human readers (e.g. non-native speakers), and those that enable reliable automatic semantic analysis of the language.”

There is a workshop CNL 2009 in Italy.

Google website about Controlled Natural Language

Web Ontology Language could be a special Controlled Natural Language which is used for Semantic Web. OWL (Web Ontology Language)

Posted in Thesis