|
• Home
• People
• Projects
Student Projects
• Publications
Ph.D. Theses
• Events
NLP Meetings
OTSLAC Meetings
NLP Calendar
• Tools
• NLP Lab
• Internal
• Speech Lab
• CCLS
|
Tools
For information on commercial use of any of these tools, please
contact Columbia University's Science & Technology Ventures, stvinfo@columbia.edu, phone number
(+1) 212-854-8444.
LCseg (v1.x)
Developed by Michel Galley
A domain-independent discourse segmenter based on lexical cohesion.
Licensing agreement
LexChainer (v1.x)
Developed by Michel Galley
A tool to find semantically related words within unrestricted texts.
Licensing agreement
LinkIT
A tool for identifying and relating noun phrases within a document.
Licensing agreement
Centrifuser
Developed by Min-Yen Kan
Centrifuser is a domain- and genre-specific multidocument summarization system. It builds both extract based summary as well as indicative document cluster summaries. The extract summary gives a high level overview of the query topic suitable for browsers. The indicative document cluster summaries differentiate the documents from each other as much as possible to route users to particular documents that can meet their underspecified information needs. Centrifuser was developed as part of the NSF's DLI 2 initiative and focuses on patient health care documents.
Licensing agreement
Annotated Bibliography Corpus
Developed by Min-Yen Kan
We have collected 2000 annotated bibliography entries from the web and put them into a standardized XML format. We have further annotated 100 of these entries with semantic tags that discuss the types of document-derived and metadata features that play a role in these summaries. Annotated bibliography entries are a good source for doing research on corpus-based summarization; as they provide information about what to include and how to write and stylize indicative summaries.
Licensing agreement
FUF
Developed by Michael Elhadad
FUF stands for Functional Unification Formalism.
fuf-5.3.tar.gz
CFUF
Developed by Michael Elhadad and Mark Kharitonov
CFUF is A graph-based implementation of the FUF language implemented in C and embedded within a Scheme interpreter.
More
Surge
Developed by Michael Elhadad and Jacques Robin
Surge is a syntactic realization grammar for text generation.
surge.tar.gz
CREP
Developed by Duford
CREP is a regular expression finder for linguistic patterns.
Licensing agreement
Segmenter
Developed by Min-Yen Kan
Segmenter is a Text Segmentation program.
Licensing agreement
Verber
Developed by Min-Yen Kan, Judith Klavans and Kathleen McKeown
Verber is designed to conflate semantically related verbs together.
Licensing agreement
|
