Towards Universal Semantic Tagging
This work addresses the need for better semantic analysis in multilingual text processing, though it appears incremental as it builds on existing frameworks like the Parallel Meaning Bank.
The paper tackles the problem of universal semantic tagging by proposing a language-neutral tagset for word tokens, showing that the tags provide fine-grained semantic information and are suitable for cross-lingual semantic parsing, with baseline results presented on a small annotated corpus.
The paper proposes the task of universal semantic tagging---tagging word tokens with language-neutral, semantically informative tags. We argue that the task, with its independent nature, contributes to better semantic analysis for wide-coverage multilingual text. We 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, we annotate a small corpus with the semantic tags and present new baseline result for universal semantic tagging.