University of Tehran NLP Lab

Useful Links

Statistical Machine Translation

Stat MT : a website dedicated to research in statistical machine translation

Moses : an open source SMT System (factored and hierarchical phrase-based translation)

Giza++ : a toolkit for word alignment based on IBM Models 1-5 and an HMM word alignment model (Google code is blocked in Iran!)

SRILM : a toolkit for building and applying statistical language models (LMs)

Europarl corpus : a Parallel Corpus for Statistical Machine Translation, includes 11 European languages

OPUS : an open source parallel corpus

JRC-ACQUIS : sentence-aligned multilingual parallel corpus for 22 European languages

Taggers and Parsers

Stanford Parser : a natural language statistical parser (English, German, Chinese and Arabic)

WordNet Construction

FarsNet : the first Persian WordNet

Princeton WordNet : a large lexical database of English

EuroWordNet : a multilingual database with wordnets for several European languages

BalkaNet : a multilingual lexical database

Resources for Persian Language

Hamshahri Corpus : text collection suitable for information retrieval

Bijankhan Corpus : tagged Persian corpus

NLP Groups working on Persian Language

DBRG Group : Database Research Group, University of Tehran

Natural Language Processing Research Laboratory : Shahid Beheshti University, Tehran, Iran

Web Technology Laboratory : Ferdowsi University of Mashhad, Iran

Journals and Conferences

Upcoming Computational Linguistics / NLP Conferences

Computational Linguistics Journals and Conferences

Computational Linguistics journal
Machine Translation journal
ACL: Annual meeting of the Association for Computational Linguistics
NAACL-HLT: North American Chapter of the Association for Computational Linguistics
EMNLP: Conference on Empirical Methods on Natural Language Processing
COLING: International Conference on Computational Linguistics
CICLing: Conference on Intelligent Text Processing and Computational Linguistics
EAMT: annual meeting of the European Association for Machine Translation
LREC: International conference on Language Resources and Evaluation
WMT: ACL Workshop on Statistical Machine Translation