As I try to put my notes in order by the end of this year, I changed a series of references, most notably in the bibliography and in the links sections.

Bibliography

I just updated the bibliography, using new categories. I divided the references in two main sections:

Corpus Linguistics, Complexity and Readability Assessment

• Corpus Linguistics and Corpus Building
• Complexity and Linguistic Complexity Theory
• Text Comprehension and Readability Theory
• Readability Formulas
• Readability Assessment

Background

• General Linguistics
• Computational Linguistics
• Measurement Theory
• Philosophy of Language
• Philosophy of Technology
• Miscellaneous Tools
• Tagging and Marking

Links

First of all, I updated the links section …

Here are a few links about interesting things that I recently read.

• An article co-authored by Daniel Lemire about cleaning Project Gutenberg e-Books (i.e. removing preambles and epilogues) using a statistical (and not a rule-based) approach.

  Removing Manually-Generated Boilerplate from Electronic Texts: Experiments with Project Gutenberg e-Books by Owen Kaser and Daniel Lemire

• An article about XML compression techniques which details several alternatives, including “XML conscious compressors”, i.e. compressors which enable queries.

  Investigate state-of-the-art XML compression techniques by Sherif Sakr

• A few SSH tricks, most notably the “Operating on Remote Files Locally” which explains how to use SSHFS …

As I had to make a poster for the TALN 2011 conference to illustrate my short paper (PDF, in French), I decided to use LaTeX, even if it was not the easiest way. I am quite happy with the result (PDF).

I gathered a few links that helped me out. My impression is that there are two common models, and as I matter of fact I saw both of them at the conference. The one that I used, Beamerposter, was “made in Germany” by Philippe Dreuw, from the Informatics Department of the University of Aachen. I only had to adapt …

I recently updated the blogroll section and I also would like to share a few links:

• a huge links selection on pattern matching: Pattern Matching Pointers
• the comp.text Frequently Asked Questions (Usenet archive)
• links on annotation (page in French, links in English) collected by Karën Fort (Paris 13)

As I will be teaching LaTeX soon the LaTeX links section of the blog has expanded.

Last but not least, here is an E-Book, Mining of Massive Datasets, by A. Rajaraman and J. D. Ullmann. It was made of classes taught at Stanford and is now free to use (available chapter …

Here is my selection of introductory courses given by well-known specialists in Computer Science or Natural Language Processing and recorded so that they can be followed at home.

1. Artificial Intelligence | Natural Language Processing, Christopher D. Manning, Stanford University.
More than 20 hours, 18 lectures.
Introduction to the key topics of NLP, summary of existing models.
Lecture 12 : Dan Jurafsky as a guest lecturer.
Requires the Silverlight plugin (no comment). Transcripts available.

2. Bits, Harry R. Lewis, Harvard University.
A general overview of information as quantity and quantitative methods.
Very comprehensive lecture (data theories, internet protocols, encryption, copyright issues, laws …