[PDF][PDF] Reproducing Russian NER Baseline Quality without Additional Data.
V Malykh, A Ozerin - CDUD@ CLA, 2016 - publications.hse.ru
V Malykh, A Ozerin
CDUD@ CLA, 2016•publications.hse.ruBaseline solutions for the named entity recognition task in Russian language were
published a few years ago. These solutions rely heavily on the addition data, like databases,
and different kinds of preprocessing. Here we demonstrate that it is possible to reproduce
the quality of existing database-based solution by character-aware neural net trained on
corpus itself only.
published a few years ago. These solutions rely heavily on the addition data, like databases,
and different kinds of preprocessing. Here we demonstrate that it is possible to reproduce
the quality of existing database-based solution by character-aware neural net trained on
corpus itself only.
Abstract
Baseline solutions for the named entity recognition task in Russian language were published a few years ago. These solutions rely heavily on the addition data, like databases, and different kinds of preprocessing. Here we demonstrate that it is possible to reproduce the quality of existing database-based solution by character-aware neural net trained on corpus itself only.
publications.hse.ru
以上显示的是最相近的搜索结果。 查看全部搜索结果