Head Finders Inspection: An Unsupervised Optimization Approach
| Autor: | Martín Ariel Domínguez, Gabriel Infante-Lopez |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Parsing
Dependency (UML) Head (linguistics) Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Phrase structure rules ComputerApplications_COMPUTERSINOTHERSYSTEMS Pattern recognition computer.software_genre ComputingMethodologies_PATTERNRECOGNITION ComputingMethodologies_SYMBOLICANDALGEBRAICMANIPULATION Training phase ComputerSystemsOrganization_SPECIAL-PURPOSEANDAPPLICATION-BASEDSYSTEMS Artificial intelligence Dependency tree business computer Syntactic parsing |
| Zdroj: | Advances in Natural Language Processing ISBN: 9783642147692 IceTAL |
| Popis: | Head finder algorithms are used by supervised parsers during their training phase to transform phrase structure trees into dependency ones. For the same phrase structure tree, different head finders produce different dependency trees. Head finders usually have been inspired on linguistic bases and they have been used by parsers as such. In this paper, we present an optimization set-up that tries to produce a head finder algorithm that is optimal for parsing. We also present a series of experiments with random head finders. We conclude that, although we obtain some statistically significant improvements using the optimal head finder, the experiments with random head finders show that random changes in head finder algorithms do not impact dramatically the performance of parsers. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|