|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ЦЭМИ РАН |
||
Filling the gaps with rules and networksстатья
- Автор: Alexey Sorokin
- Сборник: Компьютерная лингвистика и интеллектуальные Технологии. По материалам ежегодной международной конференции Диалог- 2019
- Том: 18
- Год издания: 2019
- Место издания: РГГУ М
- Первая страница: 162
- Последняя страница: 175
- Аннотация: In this paper we describe rule-based and neural approaches to gapping resolution task for Russian language. Our study was conducted on the material of AGRR-2019 Shared Task. We demonstrate that neural model definitively outperforms the rule-based one even when only 2000 annotated sentences are available. The rule-based model took the 6th place in AGRR-2019 competition (2nd in terms of precision), while the neural one was better than the second-ranked system.
- Добавил в систему: Сорокин Алексей Андреевич