File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Neural enquirer: learning to query tables in natural language
Title | Neural enquirer: learning to query tables in natural language |
---|---|
Authors | |
Issue Date | 2016 |
Publisher | International Joint Conferences on Artificial Intelligence. The online Conference Proceedings' website is located at http://www.ijcai.org/Proceedings/2016 |
Citation | The 25th International Joint Conference on Artificial Intelligence (IJCAI-16), New York, NY., 9-15 July 2016. In Conference Proceedings, 2016, p. 2308-2314 How to Cite? |
Abstract | 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 series of neural network components called “executors”. Executors model query operations and compute intermediate execution results in the form of table annotations at different levels. NEURAL ENQUIRER can be trained with gradient descent, with which the representations of queries and the KB table are jointly optimized with the query execution logic. The training can be done in an end-to-end fashion, and it can also be carried out with stronger guidance, e.g., step-by-step supervision for complex queries. NEURAL ENQUIRER is one step towards building neural network systems that can understand natural language in real-world tasks. As a proof-of-concept, we conduct experiments on a synthetic QA task, and demonstrate that the model can learn to execute reasonably complex NL queries on small-scale KB tables. |
Persistent Identifier | http://hdl.handle.net/10722/232179 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yin, P | - |
dc.contributor.author | Lu, Z | - |
dc.contributor.author | Li, H | - |
dc.contributor.author | Kao, BCM | - |
dc.date.accessioned | 2016-09-20T05:28:16Z | - |
dc.date.available | 2016-09-20T05:28:16Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | The 25th International Joint Conference on Artificial Intelligence (IJCAI-16), New York, NY., 9-15 July 2016. In Conference Proceedings, 2016, p. 2308-2314 | - |
dc.identifier.isbn | 978-1-57735-771-1 (v. 4-6) | - |
dc.identifier.uri | http://hdl.handle.net/10722/232179 | - |
dc.description.abstract | 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 series of neural network components called “executors”. Executors model query operations and compute intermediate execution results in the form of table annotations at different levels. NEURAL ENQUIRER can be trained with gradient descent, with which the representations of queries and the KB table are jointly optimized with the query execution logic. The training can be done in an end-to-end fashion, and it can also be carried out with stronger guidance, e.g., step-by-step supervision for complex queries. NEURAL ENQUIRER is one step towards building neural network systems that can understand natural language in real-world tasks. As a proof-of-concept, we conduct experiments on a synthetic QA task, and demonstrate that the model can learn to execute reasonably complex NL queries on small-scale KB tables. | - |
dc.language | eng | - |
dc.publisher | International Joint Conferences on Artificial Intelligence. The online Conference Proceedings' website is located at http://www.ijcai.org/Proceedings/2016 | - |
dc.relation.ispartof | Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16) | - |
dc.title | Neural enquirer: learning to query tables in natural language | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Kao, BCM: kao@cs.hku.hk | - |
dc.identifier.authority | Kao, BCM=rp00123 | - |
dc.identifier.hkuros | 264585 | - |
dc.identifier.spage | 2308 | - |
dc.identifier.epage | 2314 | - |
dc.publisher.place | United States | - |
dc.customcontrol.immutable | sml 161007 | - |