Training dependency parsers by jointly optimizing multiple objectives
US8660969B1 · kind B1 · utility
10Cited by
0References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 30, 2011 |
| Grant date | Feb 25, 2014 |
| Priority date | — |
| Expiry date | Jun 6, 2032 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/205
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A plurality of highest intrinsically-ranked parser outputs are scored using an extrinsic metric that is relevant to one or more downstream applications. The parser can be trained by using an extrinsically highly-ranked parse selected from among the intrinsically highly-ranked parses. The selected parse need not be the highest intrinsically-ranked parse. In this way, a parser can be trained to produce better results for downstream applications.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.