Creating a Hybrid Rule and Neural Network Based Semantic Tagger using Silver Standard Data: the PyMUSAS framework for Multilingual Semantic Annotation
This work addresses the problem of limited evaluation and training data for semantic tagging in the USAS framework, benefiting researchers in multilingual NLP, though it is incremental as it builds on existing rule-based systems.
The authors tackled the lack of extensive evaluation for the USAS semantic tagging framework by performing the largest evaluation across five languages, including a new Chinese dataset, and created a hybrid rule-neural system that enhances rule-based tagging with neural models, releasing all resources openly.
Word Sense Disambiguation (WSD) has been widely evaluated using the semantic frameworks of WordNet, BabelNet, and the Oxford Dictionary of English. However, for the UCREL Semantic Analysis System (USAS) framework, no open extensive evaluation has been performed beyond lexical coverage or single language evaluation. In this work, we perform the largest semantic tagging evaluation of the rule based system that uses the lexical resources in the USAS framework covering five different languages using four existing datasets and one novel Chinese dataset. We create a new silver labelled English dataset, to overcome the lack of manually tagged training data, that we train and evaluate various mono and multilingual neural models in both mono and cross-lingual evaluation setups with comparisons to their rule based counterparts, and show how a rule based system can be enhanced with a neural network model. The resulting neural network models, including the data they were trained on, the Chinese evaluation dataset, and all of the code have been released as open resources.