HPE: Answering Complex Questions over Text by Hybrid Question Parsing and Execution

Ye Liu, Semih Yavuz, Rui Meng, Dragomir Radev, Caiming Xiong, Shafiq Joty, Yingbo Zhou


Abstract
The dominant paradigm of textual question answering systems is based on end-to-end neural networks, which excels at answering natural language questions but falls short on complex ones. This stands in contrast to the broad adaptation of semantic parsing approaches over structured data sources (e.g., relational database, knowledge graphs), that convert natural language questions to logical forms and execute them with query engines. Towards combining the strengths of neural and symbolic methods, we propose a framework of question parsing and execution on textual QA. It comprises two central pillars: (1) We parse the question of varying complexity into an intermediate representation, named H-expression, which is composed of simple questions as the primitives and symbolic operations representing the relationships among them; (2) To execute the resulting H-expressions, we design a hybrid executor, which integrates the deterministic rules to translate the symbolic operations with a drop-in neural reader network to answer each decomposed simple question. Hence, the proposed framework can be viewed as a top-down question parsing followed by a bottom-up answer backtracking. The resulting H-expressions closely guide the execution process, offering higher precision besides better interpretability while still preserving the advantages of the neural readers for resolving its primitive elements. Our extensive experiments on MuSiQue, 2WikiQA, HotpotQA, and NQ show that the proposed parsing and hybrid execution framework outperforms existing approaches in supervised, few-shot, and zero-shot settings, while also effectively exposing its underlying reasoning process.
Anthology ID:
2023.findings-emnlp.293
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4437–4451
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.293
DOI:
10.18653/v1/2023.findings-emnlp.293
Bibkey:
Cite (ACL):
Ye Liu, Semih Yavuz, Rui Meng, Dragomir Radev, Caiming Xiong, Shafiq Joty, and Yingbo Zhou. 2023. HPE: Answering Complex Questions over Text by Hybrid Question Parsing and Execution. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4437–4451, Singapore. Association for Computational Linguistics.
Cite (Informal):
HPE: Answering Complex Questions over Text by Hybrid Question Parsing and Execution (Liu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.findings-emnlp.293.pdf