ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering

Yu Gu, Yu Su


Abstract
Question answering on knowledge bases (KBQA) poses a unique challenge for semantic parsing research due to two intertwined challenges: large search space and ambiguities in schema linking. Conventional ranking-based KBQA models, which rely on a candidate enumeration step to reduce the search space, struggle with flexibility in predicting complicated queries and have impractical running time. In this paper, we present ArcaneQA, a novel generation-based model that addresses both the large search space and the schema linking challenges in a unified framework with two mutually boosting ingredients: dynamic program induction for tackling the large search space and dynamic contextualized encoding for schema linking. Experimental results on multiple popular KBQA datasets demonstrate the highly competitive performance of ArcaneQA in both effectiveness and efficiency.
Anthology ID:
2022.coling-1.148
Original:
2022.coling-1.148v1
Version 2:
2022.coling-1.148v2
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1718–1731
Language:
URL:
https://aclanthology.org/2022.coling-1.148
DOI:
Bibkey:
Cite (ACL):
Yu Gu and Yu Su. 2022. ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1718–1731, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering (Gu & Su, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.148.pdf
Code
 dki-lab/arcaneqa