| US 7,464,026 B2 | ||
| Semantic analysis system for interpreting linguistic structures output by a natural language linguistic analysis system | ||
| Michael V. Calcagno, Kirkland, Wash. (US); Par Jonas Barklund, Kirkland, Wash. (US); Lei Zhao, Sammamish, Wash. (US); Saliha Azzam, Redmond, Wash. (US); Sonja S. Knoll, Redmond, Wash. (US); and Su Chang, Woodinville, Wash. (US) | ||
| Assigned to Microsoft Corporation, Redmond, Wash. (US) | ||
| Filed on Dec. 19, 2006, as Appl. No. 11/641,251. | ||
| Application 11/641251 is a continuation of application No. 10/047462, filed on Jan. 14, 2002, granted, now 7,177,799. | ||
| Prior Publication US 2007/0100604 A1, May 03, 2007 | ||
| Int. Cl. G06F 17/27 (2006.01); G06F 17/00 (2006.01) | ||
| U.S. Cl. 704—9 [704/270; 707/101; 707/102] | 15 Claims |
| 1. A method of interpreting a linguistic representation of a textual input, comprising:
receiving a linguistic discourse representation structure (DRS) as the linguistic representation of the textual input;
receiving an entity-and-relation model of a non-linguistic domain;
generating a semantic discourse representation structure (SemDRS) in terms of the entity-and-relation model and based on evidence
derived from the linguistic DRS;
receiving a set of semantic mapping rules, each rule having a first side that matches DRS segments of a specified form and
a second side that specifies at least a partial SemDRS;
applying the set of semantic mapping rules to the linguistic DRS;
identifying applicable semantic mapping rules as rules having first sides that match any segments of the linguistic DRS;
generating patterns associated with the linguistic DRS, the patterns including a plurality of partial SemDRSs corresponding
to the second sides of the applicable semantic mapping rules; and
combining some of the patterns, consistently with the entity-and-relation model, into a single combined solution pattern.
|