Symbolic Priors for RNN-based Semantic Parsing

Symbolic Priors for RNN-based Semantic Parsing

Chunyang Xiao, Marc Dymetman, Claire Gardent

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 4186-4192. https://doi.org/10.24963/ijcai.2017/585

Seq2seq models based on Recurrent Neural Networks (RNNs) have recently received a lot of attention in the domain of Semantic Parsing. While in principle they can be trained directly on pairs (natural language utterances, logical forms), their performance is limited by the amount of available data. To alleviate this problem, we propose to exploit various sources of prior knowledge: the well-formedness of the logical forms is modeled by a weighted context-free grammar; the likelihood that certain entities present in the input utterance are also present in the logical form is modeled by weighted finite-state automata. The grammar and automata are combined together through an efficient intersection algorithm to form a soft guide (“background”) to the RNN.We test our method on an extension of the Overnight dataset and show that it not only strongly improves over an RNN baseline, but also outperforms non-RNN models based on rich sets of hand-crafted features.
Keywords:
Natural Language Processing: Question Answering
Machine Learning: Deep Learning
Machine Learning: Knowledge-based Learning