Contact Information

CV - Linked in
ILPS Group
University of Amsterdam
Christof Monz
s.c.carter@uva.nl

Simon Carter:
PhD Candidate:

Supervisor:
Email:

Statistical Machine Translation,
Language Modeling and
Natural Language Processing

Materials on the subjects, compiled by Simon Carter, primarily for Simon Carter.

NLP, SMT & Computing Books

Speech and Language Processing
Foundations of Statistical Natural Language Processing
Introduction to Algorithms
Statistical Machine Translation
The Elements of Statistical Learning

Graduate Studies and Research

Because I don't yet have a PhD, these people are better placed than I to talk about life as a researcher/graduate student. Many of these links come from, and can be found with many more, here.
Does one have to be a genius to do maths?
Ten Lessons I Wish I Had Been Taught
Survival tips
Career advice from a Fields Medalist
On getting used to be stupid... for once
Tips on writing, and the research process (pdf)
general research articles
some grad school tips

Online Lectures

Stanford CS229 Machine Learning Lectures
Stanford CS224N Natural Language Processing Lectures
University of Heidelberg Introduction to Statistical Parsing
MIT 6.042J Mathematics for Computer Science
Data Mining tutorials by Andrew Moore

Data

Europarl Corpus
Linguistic Data Consortium
UCI Machine Learning Repository
Glasgow's stop word list

Photos

Research Interests

I am interested in the statistics of natural language and the application of machine learning techniques to nlp problems. Currently, I work on language models in the context of Statistical Machine Translation. I am interested in going beyond standard n-gram models, improving their abilities within the generative and discriminative contexts.

Publications

Simon Carter, Manos Tsagkias, Wouter Weerkamp Microblog language identification: overcoming the limitations of short, unedited and idiomatic text In Language Resources and Evaluation, to appear paper (pre-print): pdf.

Simon Carter, Christof Monz Syntactic Discriminative Language Model Rerankers for Statistical Machine Translation In Machine Translation Journal, to appear paper:pdf.

Wouter Weerkamp, Simon Carter, Manos Tsagkias How People use Twitter in Different Languages In 3rd International Conference on Web Science (WebSci 2011), paper:pdf poster:pdf.

Simon Carter, Manos Tsagkias, Wouter Weerkamp Twitter hashtags: Joint Translation and Clustering In 3rd International Conference on Web Science (WebSci 2011), paper:pdf poster:pdf.

Simon Carter, Manos Tsagkias, Wouter Weerkamp Semi-Supervised Priors for Microblog Language Identification In Dutch-Belgian Information Retrieval workshop (DIR 2011) paper:pdf poster:pdf.

Simon Carter, Christof Monz. Discriminative Syntactic Reranking for Statistical Machine Translation. In Proceedings of the Association of Machine Translation in the Americas (AMTA 2010), pp.3-12, 2010 pdf.

Simon Carter, Christof Monz. Parsing Statistical Machine Translation Output. In Proceedings of the Language & Technology Conference (LTC 2009), 2009 pdf.

Simon Carter, Christof Monz, Sirvan Yahyaei. The QMUL System Description for IWSLT 2008. In Proceedings of the International Workshop on Spoken Language Translation (IWSLT 2008), pp.104-107, 2008 pdf

Posters

Journals in no specific order

ACM Computing Surveys
ACM Transactions on Speech and Language Processing
Computational Linguistics
Computer Speech and Language
Cryptologia
International Journal of Translation
Journal of Artificial Intelligence Research
Journal of Artificial Intelligence
Journal of Logic and Computation
Journal of Machine Learning Research
Journal of Natural Language Engineering
Machine Learning
Machine Translation

Groups in no specific order

ILPS Group, University of Amsterdam
Edinburgh SMT Group
Stanford NLP Group
Mircrosoft Machine Learning and Applied Statistics Group
Carnegie Mellon Machine Learning Department
John Hopkins LSP Center
Rochester Machine Translation Group
Oxford CL Group
Cambridge Natural Language and Information Processing Group
Cambridge SMT Group
FBK

Blogs in no specific order

Machine Learning (Theory)
Readings in Machine Learning
Natural Language Processing
Language Log
Mathematics and Computation
Tasty Research
Babel's Dawn
Jurgen Van Gael Blog on ML topics
On recommender systems
Matt Might

ILPS/UvA stuff

ILPS Twiki
ILPS PhD blog
ILPS Machines
UvA Staff Website (self-service)
UvA bibliotheek
Picarata

Summer Schools

Machine Learning Summer School 2009
21st European Summer School in Logic, Language and Information (ESSLLI)

Useful Links

ACL Wiki
MT-Eval 08 Results
MT-Eval 06 Results
Call For Papers Wiki
2009 Computational Linguistics Conferences compiled by Joel Tetreault
Reading list on Bayesian modeling for language compiled by Sharon Goldwater
Collection of resources for cross-lingual information retrieval
Online learning articles collection of articles on online learning
Useful links page compiled by SIGNLL
Collection of various software tools
Latex Packages for tree drawing
Maths Refresher
UCL English Grammar guide for the majority of state educated Brits who get no grammar tuition at all
Intro, Papers and Resources for LMs
ILP for NLP
Bib on Adaptive Language Modelling
Hal DaumÃ©'s What To See
Multi-lingual corpra/stemmers/stop-word list

Free/Open Source Software

R for Statisical Computations
Octave for Numerical Computations
OpenNLP for Java NLP tools
OpenNLP MAXENT for Java Maxmimum Entropy tools
gnuplot free plotting software and here's a guide on using it, and another.
Moses an Open Source SMT System
Evalb a bracket scoring program
Carmel a finite-state transducer package
JabRef a Java based reference manager
TreeForm software for Syntax Tree Drawing
Weka an ML toolkit
SALM a Suffx Array toolkit
Multi-SALM a trivial server/client script I wrote that provides same functionality of FreqOfNgrams of SALM package, but uses forks and serves requests via sockets. Online instructions are available here

Online Translation

Google Translate
Babel Fish
sampark system (experimental)

SMT/LM Toolkits

SRILM
IRSTLM
CMU-Cambridge
GIZA++
tercom for calculating translation error rate

Parsers and Taggers

Collins Parser
Charniak Parser
Dan Bikel's Parser an implementaion of Collins Model 2 which can be re-trained and is more robust than Collins own Parser.
Stanford Parser
MXPOST a POS tagger
tree tagger a POS tagger

Companies doing SMT & ASR

Language Weaver
BBN
SRI