A Globally Normalized Neural Model for Semantic Parsing
This work addresses a specific bottleneck in semantic parsing for natural language processing, but it is incremental as it shows limited scalability.
The paper tackled the label bias problem in semantic parsing by proposing a globally normalized neural model that predicts real-valued scores instead of probabilities, and it outperformed locally normalized models on small datasets but did not improve on a large dataset.
In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias problem. Experiments show that our approach outperforms locally normalized models on small datasets, but it does not yield improvement on a large dataset.