Symbolic Priors for RNN-based Semantic Parsing

Abstract : 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.
Type de document :
Communication dans un congrès
wenty-sixth International Joint Conference on Artificial Intelligence (IJCAI-17) , Aug 2017, Melbourne, Australia. pp.4186 - 4192, 2017, 〈10.24963/ijcai.2017/585〉
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01623808
Contributeur : Claire Gardent <>
Soumis le : mercredi 25 octobre 2017 - 16:44:45
Dernière modification le : mardi 24 avril 2018 - 13:30:47
Document(s) archivé(s) le : vendredi 26 janvier 2018 - 15:18:30

Fichier

2017-IJCAI-chunyang.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Citation

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, 2017, 〈10.24963/ijcai.2017/585〉. 〈hal-01623808〉

Partager

Métriques

Consultations de la notice

259

Téléchargements de fichiers

124