Coupling Distributed and Symbolic Execution for Natural Language Queries

Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:2518-2526, 2017.

Abstract

Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires multiple steps of execution because queries may have complicated structures. In previous studies, researchers have developed either fully distributed executors or symbolic executors for table querying. A distributed executor can be trained in an end-to-end fashion, but is weak in terms of execution efficiency and explicit interpretability. A symbolic executor is efficient in execution, but is very difficult to train especially at initial stages. In this paper, we propose to couple distributed and symbolic execution for natural language queries, where the symbolic executor is pretrained with the distributed executor’s intermediate execution results in a step-by-step fashion. Experiments show that our approach significantly outperforms both distributed and symbolic executors, exhibiting high accuracy, high learning efficiency, high execution efficiency, and high interpretability.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-mou17a, title = {Coupling Distributed and Symbolic Execution for Natural Language Queries}, author = {Lili Mou and Zhengdong Lu and Hang Li and Zhi Jin}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {2518--2526}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/mou17a/mou17a.pdf}, url = {https://proceedings.mlr.press/v70/mou17a.html}, abstract = {Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires multiple steps of execution because queries may have complicated structures. In previous studies, researchers have developed either fully distributed executors or symbolic executors for table querying. A distributed executor can be trained in an end-to-end fashion, but is weak in terms of execution efficiency and explicit interpretability. A symbolic executor is efficient in execution, but is very difficult to train especially at initial stages. In this paper, we propose to couple distributed and symbolic execution for natural language queries, where the symbolic executor is pretrained with the distributed executor’s intermediate execution results in a step-by-step fashion. Experiments show that our approach significantly outperforms both distributed and symbolic executors, exhibiting high accuracy, high learning efficiency, high execution efficiency, and high interpretability.} }
Endnote
%0 Conference Paper %T Coupling Distributed and Symbolic Execution for Natural Language Queries %A Lili Mou %A Zhengdong Lu %A Hang Li %A Zhi Jin %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-mou17a %I PMLR %P 2518--2526 %U https://proceedings.mlr.press/v70/mou17a.html %V 70 %X Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires multiple steps of execution because queries may have complicated structures. In previous studies, researchers have developed either fully distributed executors or symbolic executors for table querying. A distributed executor can be trained in an end-to-end fashion, but is weak in terms of execution efficiency and explicit interpretability. A symbolic executor is efficient in execution, but is very difficult to train especially at initial stages. In this paper, we propose to couple distributed and symbolic execution for natural language queries, where the symbolic executor is pretrained with the distributed executor’s intermediate execution results in a step-by-step fashion. Experiments show that our approach significantly outperforms both distributed and symbolic executors, exhibiting high accuracy, high learning efficiency, high execution efficiency, and high interpretability.
APA
Mou, L., Lu, Z., Li, H. & Jin, Z.. (2017). Coupling Distributed and Symbolic Execution for Natural Language Queries. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:2518-2526 Available from https://proceedings.mlr.press/v70/mou17a.html.

Related Material