Answering Conversational Questions on Structured Data without Logical Forms

Thomas Mueller, Francesco Piccinno, Peter Shaw, Massimo Nicosia, Yasemin Altun


Abstract
We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. We encode tables as graphs using a graph neural network model based on the Transformer architecture. The answers are then selected from the encoded graph using a pointer network. This model is appropriate for processing conversations around structured data, where the attention mechanism that selects the answers to a question can also be used to resolve conversational references. We demonstrate the validity of this approach with competitive results on the Sequential Question Answering (SQA) task.
Anthology ID:
D19-1603
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5902–5910
Language:
URL:
https://aclanthology.org/D19-1603
DOI:
10.18653/v1/D19-1603
Bibkey:
Cite (ACL):
Thomas Mueller, Francesco Piccinno, Peter Shaw, Massimo Nicosia, and Yasemin Altun. 2019. Answering Conversational Questions on Structured Data without Logical Forms. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5902–5910, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Answering Conversational Questions on Structured Data without Logical Forms (Mueller et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1603.pdf
Data
SQA