Semantic Operator Prediction and Applications
This addresses semantic parsing efficiency for NLP applications, but appears incremental as it builds on existing models like CopyNet and recursive neural nets.
The paper tackles semantic parsing challenges by implementing QDMR formalism using a sequence-to-sequence model with attention that uses only part-of-speech tags as word representations to simplify training and avoid dimensionality/overfitting issues, achieving unspecified results.
In the present paper, semantic parsing challenges are briefly introduced and QDMR formalism in semantic parsing is implemented using sequence to sequence model with attention but uses only part of speech(POS) as a representation of words of a sentence to make the training as simple and as fast as possible and also avoiding curse of dimensionality as well as overfitting. It is shown how semantic operator prediction could be augmented with other models like the CopyNet model or the recursive neural net model.