Computational Linguistics Reading Group

I will present the task of universal semantic tagging — tagging word tokens with language-neutral, semantically informative tags. I will argue that the task, with its independent nature, contributes to better semantic analysis for wide-coverage multilingual text. I will present the initial version of the semantic tagset and show that (a) the tags provide semantically fine-grained information, and (b) they are suitable for cross-lingual semantic parsing. An application of the semantic tagging in the Parallel Meaning Bank supports both of these points as the tags contribute to formal lexical semantics and their cross-lingual projection. As a part of the application, a small corpus with the semantic tags was annotated and a new baseline result for universal semantic tagging will be presented.