Semantic Tagging with Deep Residual Networks
This work addresses semantic parsing for multilingual applications, though it appears incremental as it adapts existing ResNet architectures to a new task.
The authors introduced a novel semantic tagging task for multilingual semantic parsing and developed the first tagger using deep residual networks, achieving state-of-the-art accuracy of 95.71% on English Universal Dependencies POS tagging.
We propose a novel semantic tagging task, sem-tagging, tailored for the purpose of multilingual semantic parsing, and present the first tagger using deep residual networks (ResNets). Our tagger uses both word and character representations and includes a novel residual bypass architecture. We evaluate the tagset both intrinsically on the new task of semantic tagging, as well as on Part-of-Speech (POS) tagging. Our system, consisting of a ResNet and an auxiliary loss function predicting our semantic tags, significantly outperforms prior results on English Universal Dependencies POS tagging (95.71% accuracy on UD v1.2 and 95.67% accuracy on UD v1.3).