How Implicit Negative Evidence Improve Weighted Context-Free Grammar Induction
| Autor: | Olgierd Unold, Mateusz Gabor |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0303 health sciences
Computer science Probabilistic logic Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Negative evidence 02 engineering and technology Grammar induction Set (abstract data type) 03 medical and health sciences Rule-based machine translation 0202 electrical engineering electronic engineering information engineering Weighted context-free grammar 020201 artificial intelligence & image processing Pattern matching Special case Algorithm 030304 developmental biology |
| Zdroj: | Artificial Intelligence and Soft Computing ISBN: 9783030209148 ICAISC (2) |
| DOI: | 10.1007/978-3-030-20915-5_53 |
| Popis: | Probabilistic context-free grammars (PCFGs) or in general a weighted context-free grammars (WCFGs) are widely used in many areas of syntactic pattern matching, especially in statistical natural language parsing or biological modeling. For a given a fixed set of context–free grammar rules, probabilities of its rules can be estimated by using the Inside-Outside algorithm (IO), which is a special case of an expectation-maximization method. The IO algorithm implies only positive examples in the data given. In this paper a modified IO algorithm to estimate probabilistic parameters over implicit positive and also negative evidence is proposed. We demonstrate that a Contrastive Estimation based method outperforms a standard IO algorithm in terms of Precision, without any loss of Recall. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|