LT TTT2 System
Jump to navigation
Jump to search
The LT TTT2 System is a Shallow NLP Processing System.
- AKA: LT TTT2.
- Context:
- It uses the following pipeline::
- a Tokeniser.
- Surface Word Segmenter which supersedes LT TTT.
- a Sentence Splitter.
- a Part-of-Speech Tagger (from a third party)
- a Lemmatiser (from a third party).
- a Named Entity Recognizer (rule based).
- a Chunker.
- a Tokeniser.
- It is developed by the Edinburgh Language Technology Group.
- It uses the following pipeline::
References
2009
- http://www.ltg.ed.ac.uk/software/lt-ttt2
- Synopsis: XML-based software for shallow linguistic processing of text.
- Description: LT-TTT2 is built around the LT-XML2 programs and provides NLP components for a variety of text processing tasks such as tokenisation and sentence-splitting, chunking and rule-based named entity recognition. It includes a third party part-of-speech tagger and lemmatiser.
- http://www.ltg.ed.ac.uk/software/lt-ttt2/pipeline-doc/file/at_download
2008
- (Grover, 2008) ⇒ Claire Grover. (2008). “LT-TTT2 Example Pipelines Documentation Edinburgh Language Technology Group, July 24.
2000
- (Grover et al., 2000) ⇒ Claire Grover, Colin Matheson, Andrei Mikheev, and Marc Moens. (2000). “LT TTT - A flexible tokenisation tool.” In: Proceedings of LREC-2000.
1999
- Claire Grover, Andrei Mikheev, and Colin Matheson. (1999). “LT TTT version 1.0: text tokenisation software. http://www.ltg.ed.ac.uk/software/ttt/