Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
This addresses the problem of accurate semantic parsing for natural language processing applications, though it is incremental as it combines existing directions.
The paper tackled semantic parsing by proposing Sequence-to-Action, an end-to-end neural approach that generates semantic graphs from sentences, achieving state-of-the-art performance on the OVERNIGHT dataset and competitive results on GEO and ATIS datasets.
This paper proposes a neural semantic parsing approach -- Sequence-to-Action, which models semantic parsing as an end-to-end semantic graph generation process. Our method simultaneously leverages the advantages from two recent promising directions of semantic parsing. Firstly, our model uses a semantic graph to represent the meaning of a sentence, which has a tight-coupling with knowledge bases. Secondly, by leveraging the powerful representation learning and prediction ability of neural network models, we propose a RNN model which can effectively map sentences to action sequences for semantic graph generation. Experiments show that our method achieves state-of-the-art performance on OVERNIGHT dataset and gets competitive performance on GEO and ATIS datasets.