The hunvec framework for NN-CRF-based sequential tagging

1 code implementation • LREC 2016 • Katalin Pajkossy, Attila Zs{\'e}der

For demonstrating the flexibility of our tool, we describe a set of experiments on part-of-speech and named-entity-recognition tasks, using English and Hungarian datasets, where we modify both model and training parameters, and illustrate the usage of custom features.

Feature Engineering named-entity-recognition +2

Structure Learning in Weighted Languages

no code implementations • WS 2013 • Andr{\'a}s Kornai, Attila Zs{\'e}der, G{\'a}bor Recski

Language Modelling

Rapid creation of large-scale corpora and frequency dictionaries

no code implementations • LREC 2012 • Attila Zs{\'e}der, G{\'a}bor Recski, D{\'a}niel Varga, Andr{\'a}s Kornai

We describe, and make public, large-scale language resources and the toolchain used in their creation, for fifteen medium density European languages: Catalan, Czech, Croatian, Danish, Dutch, Finnish, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Serbian, Slovak, Spanish, and Swedish.

Sentence