Simple, Fast Semantic Parsing with a Tensor Kernel
This provides a simpler and faster alternative for semantic parsing, though it is incremental as it matches performance of more complex systems.
The paper tackled semantic parsing by using a tensor product kernel with simple feature vectors for queries and logical forms, achieving an average F1 score of 40.1% on the WebQuestions dataset.
We describe a simple approach to semantic parsing based on a tensor product kernel. We extract two feature vectors: one for the query and one for each candidate logical form. We then train a classifier using the tensor product of the two vectors. Using very simple features for both, our system achieves an average F1 score of 40.1% on the WebQuestions dataset. This is comparable to more complex systems but is simpler to implement and runs faster.