| Popis: |
Financiado para publicación en acceso aberto: Universidade de Vigo/CISUG info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2017-85160-C2-2-R/ES/AVANCES EN NUEVOS SISTEMAS DE EXTRACCION DE RESPUESTAS CON ANALISIS SEMANTICO Y APRENDIZAJE PROFUNDO info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-113230RB-C22/ES/SEQUENCE LABELING MULTITASK MODELS FOR LINGUISTICALLY ENRICHED NER: SEMANTICS AND DOMAIN ADAPTATION (SCANNER-UVIGO) In order to minimize the generalization error in neural networks, a novel technique to identify overfitting phenomena when training the learner is formally introduced. This enables support of a reliable and trustworthy early stopping condition, thus improving the predictive power of that type of modeling. Our proposal exploits the correlation over time in a collection of online indicators, namely characteristic functions for indicating if a set of hypotheses are met, associated with a range of independent stopping conditions built from a canary judgment to evaluate the presence of overfitting. That way, we provide a formal basis for decision making in terms of interrupting the learning process. As opposed to previous approaches focused on a single criterion, we take advantage of subsidiarities between independent assessments, thus seeking both a wider operating range and greater diagnostic reliability. With a view to illustrating the effectiveness of the halting condition described, we choose to work in the sphere of natural language processing, an operational continuum increasingly based on machine learning. As a case study, we focus on parser generation, one of the most demanding and complex tasks in the domain. The selection of cross-validation as a canary function enables an actual comparison with the most representative early stopping conditions based on overfitting identification, pointing to a promising start toward an optimal bias and variance control. Agencia Estatal de Investigación | Ref. TIN2017-85160-C2-2-R Agencia Estatal de Investigación | Ref. PID2020-113230RB-C22 Xunta de Galicia | Ref. ED431C 2018/50 |
Full Text from ScienceDirect