SYGMA: A System for Generalizable and Modular Question Answering Over Knowledge Bases

Sumit Neelam, Udit Sharma, Hima Karanam, Shajith Ikbal, Pavan Kapanipathi, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Young-Suk Lee, Santosh Srivastava, Cezar Pendus, Saswati Dana, Dinesh Garg, Achille Fokoue, G P Shrivatsa Bhargav, Dinesh Khandelwal, Srinivas Ravishankar, Sairam Gurajada, Maria Chang, Rosario Uceda-Sosa, Salim Roukos, Alexander Gray, Guilherme Lima, Ryan Riegel, Francois Luus, L V Subramaniam


Abstract
Knowledge Base Question Answering (KBQA) involving complex reasoning is emerging as an important research direction. However, most KBQA systems struggle with generalizability, particularly on two dimensions: (a) across multiple knowledge bases, where existing KBQA approaches are typically tuned to a single knowledge base, and (b) across multiple reasoning types, where majority of datasets and systems have primarily focused on multi-hop reasoning. In this paper, we present SYGMA, a modular KBQA approach developed with goal of generalization across multiple knowledge bases and multiple reasoning types. To facilitate this, SYGMA is designed as two high level modules: 1) KB-agnostic question understanding module that remain common across KBs, and generates logic representation of the question with high level reasoning constructs that are extensible, and 2) KB-specific question mapping and answering module to address the KB-specific aspects of the answer extraction. We evaluated SYGMA on multiple datasets belonging to distinct knowledge bases (DBpedia and Wikidata) and distinct reasoning types (multi-hop and temporal). State-of-the-art or competitive performances achieved on those datasets demonstrate its generalization capability.
Anthology ID:
2022.findings-emnlp.284
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3866–3879
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.284
DOI:
10.18653/v1/2022.findings-emnlp.284
Bibkey:
Cite (ACL):
Sumit Neelam, Udit Sharma, Hima Karanam, Shajith Ikbal, Pavan Kapanipathi, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Young-Suk Lee, Santosh Srivastava, Cezar Pendus, Saswati Dana, Dinesh Garg, Achille Fokoue, G P Shrivatsa Bhargav, Dinesh Khandelwal, Srinivas Ravishankar, Sairam Gurajada, Maria Chang, Rosario Uceda-Sosa, et al.. 2022. SYGMA: A System for Generalizable and Modular Question Answering Over Knowledge Bases. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3866–3879, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
SYGMA: A System for Generalizable and Modular Question Answering Over Knowledge Bases (Neelam et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2022.findings-emnlp.284.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2022.findings-emnlp.284.mp4