In this work, we tackle the problem of Armenian named entity recognition, providing silverand gold-standard datasets as well as establishing baseline results on popular models. We present a 163000-token named entity c...
详细信息
ISBN:
(纸本)9781728112763;9781728112756
In this work, we tackle the problem of Armenian named entity recognition, providing silverand gold-standard datasets as well as establishing baseline results on popular models. We present a 163000-token named entity corpus automatically generated and annotated from Wikipedia, and another 53400token corpus of news sentences with manual annotation of people, organization and location named entities. The corpora were used to train and evaluate several popular named entity recognition models. Alongside the datasets, we release 50-, 100-, 200-, 300dimensional GloVe word embeddings trained on a collection of Armenian texts from Wikipedia, news, blogs, and encyclopedia.
The syst.m FT/sub /spl les// of ordering constraints over feature trees has been introduced as an extension of the syst.m FT of equality constraints over feature trees. We investigate the first-order theory of FT/sub ...
详细信息
The syst.m FT/sub /spl les// of ordering constraints over feature trees has been introduced as an extension of the syst.m FT of equality constraints over feature trees. We investigate the first-order theory of FT/sub /spl les// and its fragments, both over finite trees and over possibly infinite trees. We prove that the first-order theory of FT/sub /spl les// is undecidable, in contrast to the first-order theory of FT which is well-known to be decidable. We determine the complexity of the entailment problem of FT/sub /spl les// with existential quantification to be PSPACE-complete, by proving its equivalence to the inclusion problem of non-deterministic finite automata. Our reduction from the entailment problem to the inclusion problem is based on a new algorithm that, given an existential formula of FT/sub /spl les//, computes a finite automaton which accepts all its logic consequences.
暂无评论