Dalhousie University >> Faculty of Computer Science >> DNLP Group Login

Dalhousie Natural Language Processing Group


[ About | Corpora | Meetings | People | Projects | Resources ]

Meetings

Meetings time for Summer 2007: Fridays at 11:30 a.m. in Teaching Lab 3.

List of past meetings (not up to date).


About

The Dalhousie Natural Language Processing Group (DNLP) provides information about NLP-related research conducted at the University of Dalhousie, and it isa forum for discussion, collaboration, and interaction between researchers interested in the philosophies, theories, and applications related to NLP.

The Dalhousie NLP Group was formed in May 2003 by a combined effort from faculty members and graduate students.

Some of the topics the group is interested in are: language modeling, information extraction, information retrieval, question answering, parsing, text mining, data mining, text categorization, document clustering, speech recognition, automatic translation, syntactic and semantic analysis.

Related complementary groups at Dalhousie: MALNIS, WIFL

Top ^


Associated Members

Syed Sibte Raza Abidi Faculty
Nick Cercone  Faculty, York
Christian Blouin  Faculty
Qigang Gao  Faculty
Dawn Jutla  Faculty, SMU
Vlado Keselj  Faculty
Jasmina Milicevic  Faculty, FASS
Evangelos E. Milios Faculty
Arnold Mitnitski  Faculty
Norbert Zeh  Faculty
Tony Abou-Assaleh Ph.D. Candidate
Daan He  Ph.D. Candidate
John Healy  Ph.D. Candidate
Chris Jordan  Ph.D. Candidate
Haibin Liu  Ph.D. Candidate
Lalita Narupiyakul Ph.D. Candidate
Qiufen Qi   Ph.D. Candidate
Hathai Tanta-ngai   Ph.D. Candidate
Jane Tougas   Ph.D. Candidate
Ji Zhang  Ph.D. Candidate
Yongzheng Zhang  Ph.D. Candidate
Jiye Li   Visiting Scholar
Chutima Pisarn   Visiting Scholar
Haewon Chung  MACS Candidate
Jonathan Doyle MCS
Chris Xining Gu  MEC Candidate
Singer XJ Wang MS Candidate
Gang Wei   MS Candidate
Charles Ikeson  UG Student
Chris Whidden UG Student

Alumni

Philip O'Brien  MS2007
Zheyuan Yu  MS2007
Lina Hdeib  UGRS
Haixia Tang  MACS2005
Pradeep Monga  MS 2005
Samuel Yonas  MACS
Asad Rashid Satti MS
Sittichai Jiampojamarn MS
Jiayun Guo MS
Yingbo Miao  MS
Calvin Thomas MS

For questions or comments regarding this research group (e.g., joining the group and e-mail list) you can contact Vlado Keselj or Tony Abou-Assaleh.

Top ^


Projects

Top ^


Resources

General Links
- General resources - Conferences and workshops - Links to similar groups - Forward Pointers
Preprocessing
- Sentence Splitters (sentencizers, sentence boundary detectors):
POS Tagging
- QTag
- Software Plaza:Brill's tagger
- Ingo's collection of POS taggers
- CLAWS part-of-speech tagger
- UCREL CLAWS7 Tagset
- AI repository: taggers
- AI repository: Brill's tagger
Text Categorization
- Spam detection
- Encoding identification
- Language identification
- Sentiment classification
- Topic categorization
- Authorship attribution
- Other
Text Summarization

Phonology
- Merriam-Webster's Pronunciation Guide
- Merriam-Webster's Pronunciation Symbols
Morphology
- Using eigenvectors of the bigram graph to infer morpheme identity, by Mikhail Belkin and John Goldsmith, 2002.
Lexical Semantics
- WordNet: Home, On-line
- Global WordNet Association
Unification
- "Unification: A Multidisciplinary Survey," Kevin Knight, ACM Computing Surveys, 21(1), pages 93-124, 1989.

Grammar Formalisms

- Unification-based grammars
- Head-driven Phrase Structure Grammar (HPSG)
- Lexical Functional Grammar (LFG)
- Stochastic Unification-based Grammars
Parsers
- ALE unification-based parser, coverage: medium
- LKB unification-based parser, coverage: medium
- PC-PATR unification-based parser, coverage: small
- Stefy unification-based parser, coverage: small
- NLP Software (includes parser list)
- Parser comparison (several parsers referenced)
- Collins parser, coverage: large
- Link Grammar parser, coverage: large
- Apple Pie Parser
- Probabilistic Word Graph Parser: Java Source & Documentation, Bob Carpenter, coverage: small
- MINIPAR parser, coverage: medium
Machine Translation
Semantic Annotation
Information Extraction
- Chelba, Mahajan: Information Extraction Using the Structured Language Model
Question Answering
- TREC
- TREC-8 Proceedings (1999)
- TREC-9 Proceedings (2000)
- TREC-10 Proceedings (2001)
- TREC-11 Proceedings (2002)

Cross-Language IR
- CLEF - Cross Language Evaluation Forum
- "Japanese/English Cross-Language Information Retrieval: Exploration of Query Translation and Transliteration," by Atsushi Fujii and Tetsuya Ishikawa, Computers and the Humanities, Vol.35, No.4, pp.389-420, 2001.
NLP Tools
- GATE: General Architecture for Text Engineering, used in Information Extraction
- OpenNLP: Open source NLP, project umbrella
- N-gram Statistics Package (NSP), by Pedersen at al.
- NLTK: the Natural Language Toolkit.
- Morphix-NLP: a Live CD Linux distribution with a rich collection of NLP applications.
- Knorpora: a modified version of the Knoppix Live CD for students of corpus-based computational linguistics.

NL Corpora
- Project Gutenberg
- Alex Catalogue of Electronic Texts
- Russian novels
- Hansard - Parallel English/French Corpus - Official records of Canadian Parliament - Europarl Parallel Corpus

Top ^


DNLP website is maintained by Vlado Keselj.
© 2003-7 DNLP Group, Dalhousie University. Last Updated: 16-Jan-2008
.