Semantic Tagging with LSTM-CRF

Tagging can always be seen as an initial step in any task such as dependency parsing as is done in (Vacareanu et al. 2020) or part of speech(POS) tagging as well as named entity recognition(NER) tagging. POS tagging as well as NER tagging for semantic parsing is very restricted and they determine lexical semantics with some shortcomings. Univeral semantic tagging(semtagging) is motivated to reduce and compensate such limitations and shortcomings. Another motivation is that parsing community are shifting from syntactic dependency tree parsing to semantic dependency graph parsing and semtagging could be seen as an initial step in these investigations. Semantic tagging is the task of assigning language-neutral semantic categories to words. The necessity of semantic tagging can be well realized in recent research on semantic parsing.