Coupling Distributed and Symbolic Execution for Natural Language Queries
نویسندگان
چکیده
In this paper, we propose to combine neural execution and symbolic execution to query a table with natural languages. Our approach makes use the differentiability of neural networks and transfers (imperfect) knowledge to the symbolic executor before reinforcement learning. Experiments show our approach achieves high learning efficiency, high execution efficiency, high interpretability, as well as high performance.1
منابع مشابه
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
Relational databases store a significant amount of the worlds data. However, accessing this data currently requires users to understand a query language such as SQL. We propose Seq2SQL, a deep neural network for translating natural language questions to corresponding SQL queries. Our model uses rewards from inthe-loop query execution over the database to learn a policy to generate the query, wh...
متن کاملNeural enquirer: learning to query tables in natural language
We propose NEURAL ENQUIRER — a neural network architecture for answering natural language (NL) questions based on a knowledge base (KB) table. Unlike existing work on end-to-end training of semantic parsers [Pasupat and Liang, 2015; Neelakantan et al., 2015], NEURAL ENQUIRER is fully “neuralized”: it finds distributed representations of queries and KB tables, and executes queries through a seri...
متن کاملSeq2sql: Generating Structured Queries
Relational databases store a significant amount of the world’s knowledge. However, users are limited in their ability to access this knowledge due to a lack of understanding of query languages such as SQL. We propose Seq2SQL, a deep neural network for translating natural language questions to corresponding SQL queries. Our model leverages the structure of SQL queries to reduce the output space ...
متن کاملNatural Language
We propose NEURAL ENQUIRER — a neural network architecture for answering natural language (NL) questions given a knowledge base (KB) table. Unlike previous work on end-to-end training of semantic parsers, NEURAL ENQUIRER is fully “neuralized”: it gives distributed representations of queries and KB tables, and executes queries through a series of differentiable operations. The model can be train...
متن کاملDynamic Symbolic Execution for Testing Distributed Objects
This paper extends dynamic symbolic execution to distributed and concurrent systems. Dynamic symbolic execution can be used in software testing to systematically identify equivalence classes of input values and has been shown to scale well to large systems. Although mainly applied to sequential programs, this scalability makes it interesting to consider the technique in the distributed and conc...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017