Symbolic Priors for RNN-based Semantic Parsing - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Symbolic Priors for RNN-based Semantic Parsing


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 base-line, but also outperforms non-RNN models based on rich sets of hand-crafted features.
Fichier principal
Vignette du fichier
2017-IJCAI-chunyang.pdf (511.03 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-01623808 , version 1 (25-10-2017)



Chunyang Xiao, Marc Dymetman, Claire Gardent. Symbolic Priors for RNN-based Semantic Parsing. wenty-sixth International Joint Conference on Artificial Intelligence (IJCAI-17) , Aug 2017, Melbourne, Australia. pp.4186 - 4192, ⟨10.24963/ijcai.2017/585⟩. ⟨hal-01623808⟩
229 View
179 Download



Gmail Facebook Twitter LinkedIn More