Fast semantic extraction using a neural network architecture
US8180633B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 29, 2008 |
| Grant date | May 15, 2012 |
| Priority date | — |
| Expiry date | Dec 2, 2030 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/30
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system and method for semantic extraction using a neural network architecture includes indexing each word in an input sentence into a dictionary and using these indices to map each word to a d-dimensional vector (the features of which are learned). Together with this, position information for a word of interest (the word to labeled) and a verb of interest (the verb that the semantic role is being predicted for) with respect to a given word are also used. These positions are integrated by employing a linear layer that is adapted to the input sentence. Several linear transformations and squashing functions are then applied to output class probabilities for semantic role labels. All the weights for the whole architecture are trained by backpropagation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.