Research Associate Professor
New York University
- Office: 715 Broadway, 7th floor, New York, NY 10003 USA
- Phone: (212) 998-3175
- Fax: (212) 995-4123
- E-mail: Lastname AT cs DOT nyu DOT edu
- Homepage: http://nlp.cs.nyu.edu/sekine
A book I edited with Prof. Elisabete Ranchhod was published from John BenjaminsPublishing Company :
Named Entities provides critical information for many NLP applications.
Named Entity recognition and classification (NERC) in text is recognized as
one of the important sub-task of Information Extraction (IE).
The seven papers in this volume cover various interesting and informative aspects of NERC research.
Nadeau and Sekine provide an extensive survey of past NERC technologies, which should be a very useful resources for new researchers in this field. ...
ISBN 978 90 272 2249 7
I wote a preface to the Journal of Natural Language Processing (in Japanese) to encourage Japanese researchers here.
I'm interested in Research on Linguistic Knowledge Discovery and On-Demand Information Extraction, as well as many related area in Natural Language Processing technologies
Recently, I did:
My Standard Presentation Slides (10 spring)
A co-organizer of 2009 JHU summer workshop on Unsupervized Acquisition of Lexical Knowledge from N-Grams
A New York area coordinator of North American Computational Linguistic Olympiad(2009)
A co-organizer of Web People Search task 2 (WePS-2) (2008-2009).
A tutorial speaker about "Semantic Knowledge Discovery" at Japanese Annual Meeting on NLP, and JHU tutorial (2009).
The organizer of NSF Symposium on Semantic Knowledge Discovery, Organization and Use (2008).
A tutorial speaker about "Minimally Supervised Knowledge Discovery" at UPM on November 14, 2007.
A co-chair for ACL-PASCAL Workshop on Textual Entailment and Paraphrasing which will be held in Prague, in conjunction with ACL-2007.
A co-guest editor for Special Issue of Linguisticae Investigationes: Named Entities: Recognition, Classification and Use (2007).
A co-organizer for Web People Search task at SemEval (2007).
The local arrangement chair for HLT-NAACL06 held in New York City on 4-9 June, 2006.
Tools and Resources
Projects I have been working on
I'm working on the research area of Natural Language Processing,
i.e. mechanical implimentations of human languages and the science behind it.
The major topics I'm working on and I have been working on are:
- Linguistic Knowledge Discovery from corpus
- On-Demand Information Extraction (ODIE)
- Extended Named Entity
- Named Entity Disambiguation
Web People Search; name disambiguation, attribute extraction (
- English analyzer
Building sentence splitter, tokenizer, stemmer, POS tagger, chunker,
NE tagger, Dependency analyzer and parser combining corpus-based and
hand crafted methods.
- Question Answering
Answering questions based on facts writen in newspaper. Cross-Lingual QA. To solve elementary student's language test.
Text summarization using various features and the relationships between summarization and IE.
- Japanese Analyzer
- Japanese Named Entity
- Japanese IR, IE project, - IREX -
I lead an IR and IE evaluation project in Japanese which has 45 participans from Japan and U.S.A.
- English Parser
- Semantic Knowledge Acquisition
Semi or fully automatically acquire lexical dependency information from untagged corpus