STATISTICALLY DRIVEN SENTENCE REALIZING METHOD AND APPARATUS

Patent №

US 7,003,445

Granted

2006-02-21

Filed 2001

Owner

MICROSOFT CORPORATION

AI components

6

ml · nlp · speech · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

09909530

A method of, and system for, generating a sentence from a semantic representation maps the semantic representation to an unordered set of syntactic nodes. Simplified generation grammar rules and statistical goodness measure values from a corresponding analysis grammar are then used to create a tree structure to order the syntactic nodes. The sentence is then generated from the tree structure. The generation grammar is a simplified (context free) version of a corresponding full (context sensitive) analysis grammar. In the generation grammar, conditions on each rule are ignored except those directly related to the semantic representation. The statistical goodness measure values, which are calculated through an analysis training phase in which a corpus of example sentences is processed using the full analysis grammar, are used to guide the generation choice to prefer substructures most commonly found in a particular syntactic/semantic context during analysis.

AI classification

Natural language1.00
Speech1.00
Knowledge representation1.00
AI hardware1.00
Machine learning0.76
Planning0.52
Evolutionary computation0.00
Vision0.00

Ownership

MICROSOFT CORPORATION

assignment · 120490697

Assignors

HUMPHREYS, KEVIN W., WEISE, DAVID N., CALCAGNO, MICHAEL

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC