Computer Science – Computation and Language
Scientific paper
1996-06-18
Computer Science
Computation and Language
10 pages, Postscript; to appear in Proceedings Workshop on Corpus-Oriented Semantic Analysis, ECAI-96, Budapest
Scientific paper
In Data-Oriented Parsing (DOP), an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new input sentence is constructed by combining sub-analyses from the corpus in the most probable way. This approach has been succesfully used for syntactic analysis, using corpora with syntactic annotations such as the Penn Treebank. If a corpus with semantically annotated sentences is used, the same approach can also generate the most probable semantic interpretation of an input sentence. The present paper explains this semantic interpretation method, and summarizes the results of a preliminary experiment. Semantic annotations were added to the syntactic annotations of most of the sentences of the ATIS corpus. A data-oriented semantic interpretation algorithm was succesfully tested on this semantically enriched corpus.
Bod Rens
Bonnema Remko
Scha Remko
No associations
LandOfFree
A Data-Oriented Approach to Semantic Interpretation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A Data-Oriented Approach to Semantic Interpretation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Data-Oriented Approach to Semantic Interpretation will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-586490