Improving Semantic Parsing with Neural Generator-Reranker Architecture
This work addresses the precision issue in semantic parsing for natural language processing applications, representing an incremental improvement over existing neural methods.
The paper tackled the problem of low one-best precision in neural semantic parsing by proposing a generator-reranker architecture, achieving state-of-the-art results on three datasets (GEO, ATIS, and OVERNIGHT).
Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have recently achieved substantial improvements over traditional methods. Although neural semantic parsers appear to have relatively high recall using large beam sizes, there is room for improvement with respect to one-best precision. In this work, we propose a generator-reranker architecture for semantic parsing. The generator produces a list of potential candidates and the reranker, which consists of a pre-processing step for the candidates followed by a novel critic network, reranks these candidates based on the similarity between each candidate and the input sentence. We show the advantages of this approach along with how it improves the parsing performance through extensive analysis. We experiment our model on three semantic parsing datasets (GEO, ATIS, and OVERNIGHT). The overall architecture achieves the state-of-the-art results in all three datasets.