Feature-Rich Part-Of-Speech Tagging Using Deep Syntactic and Semantic Analysis.
Luchezar Jackov · Recent Advances in Natural Language Processing · 2015
This paper describes the implementation, improvement and evaluation of the machine translation (MT) system proposed by Jackov (2014) when used as a feature-rich part-ofspeech (POS) tagger for Bulgarian. The system does not rely on POS tagging for morphological disambiguation. Instead, all ambiguities are considered in parsing hypotheses that are scored and the best one is used for tagging. The system does not use automatic training on annotated corpora. Manually and automatically compiled linguistic resources are used for hypothesis derivation and scoring. BulTreeBank manually annotated corpus (Simov and Osenova, 2004) was used for evaluation, error detection and improvement.