Computational semantics in the Natural Language Toolkit

Ewan Klein

Research output: Chapter in Book/Report/Conference proceedingConference contribution


NLTK, the Natural Language Toolkit, is an open source project whose goals include providing students with software and language resources that will help them to learn basic NLP. Until now, the program modules in NLTK have covered such topics as tagging, chunking, and parsing, but have not incorporated any aspect of semantic interpretation. This paper describes recent work on building a new semantics package for NLTK. This currently allows semantic representations to be built compositionally as a part of sentence parsing,
and for the representations to be evaluated by a model checker. We present the
main components of this work, and consider comparisons between the Python implementation and the Prolog approach developed by Blackburn and Bos (2005).
Original languageEnglish
Title of host publicationIn Proceedings of the Australasian Language Technology Workshop
Number of pages8
Publication statusPublished - 2006

Fingerprint Dive into the research topics of 'Computational semantics in the Natural Language Toolkit'. Together they form a unique fingerprint.

Cite this