MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation

Swarnadeep Saha, Xinyan Yu, Mohit Bansal, Ramakanth Pasunuru, Asli Celikyilmaz


Abstract
Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low semantic coverage, hallucination, and logical inconsistency. We propose MURMUR a neuro-symbolic modular approach to text generation from semi-structured data with multi-step reasoning. MURMUR is a best-first search method that generates reasoning paths using: (1) neural and symbolic modules with specific linguistic and logical skills, (2) a grammar whose production rules define valid compositions of modules, and (3) value functions that assess the quality of each reasoning step. We conduct experiments on two diverse data-to-text generation tasks like WebNLG and LogicNLG. The tasks differ in their data representations (graphs and tables) and span multiple linguistic and logical skills. MURMUR obtains significant improvements over recent few-shot baselines like direct prompting and chain-of-thought prompting, while also achieving comparable performance to fine-tuned GPT-2 on out-of-domain data. Moreover, human evaluation shows that MURMUR generates highly faithful and correct reasoning paths that lead to 26% more logically consistent summaries on LogicNLG, compared to direct prompting.
Anthology ID:
2023.findings-acl.704
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11069–11090
Language:
URL:
https://aclanthology.org/2023.findings-acl.704
DOI:
10.18653/v1/2023.findings-acl.704
Bibkey:
Cite (ACL):
Swarnadeep Saha, Xinyan Yu, Mohit Bansal, Ramakanth Pasunuru, and Asli Celikyilmaz. 2023. MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11069–11090, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation (Saha et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.704.pdf