EMNLP 2022finding24 citations

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

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.

BibTeX
@inproceedings{neelam-etal-2022-sygma,
    title = "{SYGMA}: A System for Generalizable and Modular Question Answering Over Knowledge Bases",
    author = "Neelam, Sumit  and
      Sharma, Udit  and
      Karanam, Hima  and
      Ikbal, Shajith  and
      Kapanipathi, Pavan  and
      Abdelaziz, Ibrahim  and
      Mihindukulasooriya, Nandana  and
      Lee, Young-Suk  and
      Srivastava, Santosh  and
      Pendus, Cezar  and
      Dana, Saswati  and
      Garg, Dinesh  and
      Fokoue, Achille  and
      Bhargav, G P Shrivatsa  and
      Khandelwal, Dinesh  and
      Ravishankar, Srinivas  and
      Gurajada, Sairam  and
      Chang, Maria  and
      Uceda-Sosa, Rosario  and
      Roukos, Salim  and
      Gray, Alexander  and
      Lima, Guilherme  and
      Riegel, Ryan  and
      Luus, Francois  and
      Subramaniam, L V",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-emnlp.284/",
    doi = "10.18653/v1/2022.findings-emnlp.284",
    pages = "3866--3879"
}
SYGMA: A System for Generalizable and Modular Question Answering Over Knowledge Bases · EMNLP 2022