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.

Unsupervised word embeddings provide rich linguistic and conceptual information about words. However, they may provide weak information about domain specific semantic relations for certain tasks such as semantic parsing of natural language queries, where such information about words can be valuable. To encode the prior knowledge about the semantic word relations, we present new method as follows: We extend the neural network based lexical word embedding objective function Mikolov, et.al. 2013 by incorporating the information about relationship between entities that we extract from knowledge bases. Our model can jointly learn lexical word representations from free text enriched by the relational word embeddings from relational data (e.g., Freebase) for each type of entity relations. We empirically show on the task of semantic tagging of natural language queries that our enriched embeddings can provide information about not only short-range syntactic dependencies but also long-range semantic dependencies between words. Using the enriched embeddings, we obtain an average of 2% improvement in F-score compared to the previous baselines.