Loading...
Please wait, while we are loading the content...
Similar Documents
The estimation of stochastic context-free grammars using the Inside-Outside algorithm
| Content Provider | Semantic Scholar |
|---|---|
| Author | Solmon, Vladimir |
| Copyright Year | 2003 |
| Abstract | Using an entropy argument, it is shown that stochastic context-free grammars (SCFG’s) can model sources with hidden branching processes more efficiently than stochastic regular grammars (or equivalently HMM’s). However, the automatic estimation of SCFG’s using the Inside-Outside algorithm is limited in practice by its O(n)) complexity. In this paper, a novel pre-training algorithm is described which can give significant computational savings. Also, the need for controlling the way that non-terminals are allocated to hidden processes is discussed and a solution is presented in the form of a grammar minimization procedure. |
| File Format | PDF HTM / HTML |
| DOI | 10.1016/0885-2308(90)90022-x |
| Alternate Webpage(s) | http://web.cecs.pdx.edu/~landeckw/aml-spring-2012/slides/SolmonCs546Slides.pdf |
| Alternate Webpage(s) | https://courses.cs.washington.edu/courses/cse599d1/16sp/lari-young-90.pdf |
| Alternate Webpage(s) | https://doi.org/10.1016/0885-2308%2890%2990022-x |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
