Computer Science – Computation and Language
Scientific paper
2011-08-18
Proceedings of International Conference on Computational Semantics (IWCS) 2011, Oxford, pp:35-44
Computer Science
Computation and Language
Scientific paper
We present a system to translate natural language sentences to formulas in a formal or a knowledge representation language. Our system uses two inverse lambda-calculus operators and using them can take as input the semantic representation of some words, phrases and sentences and from that derive the semantic representation of other words and phrases. Our inverse lambda operator works on many formal languages including first order logic, database query languages and answer set programming. Our system uses a syntactic combinatorial categorial parser to parse natural language sentences and also to construct the semantic meaning of the sentences as directed by their parsing. The same parser is used for both. In addition to the inverse lambda-calculus operators, our system uses a notion of generalization to learn semantic representation of words from the semantic representation of other words that are of the same category. Together with this, we use an existing statistical learning approach to assign weights to deal with multiple meanings of words. Our system produces improved results on standard corpora on natural language interfaces for robot command and control and database queries.
Baral Chitta
Dzifcak Juraj
Gonzalez Marcos Alvarez
Zhou Jiayu
No associations
LandOfFree
Using Inverse lambda and Generalization to Translate English to Formal Languages 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 Using Inverse lambda and Generalization to Translate English to Formal Languages, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Using Inverse lambda and Generalization to Translate English to Formal Languages will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-107594