multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning

Swarnadeep Saha, Prateek Yadav, Mohit Bansal


Abstract
We focus on a type of linguistic formal reasoning where the goal is to reason over explicit knowledge in the form of natural language facts and rules (Clark et al., 2020). A recent work, named PRover (Saha et al., 2020), performs such reasoning by answering a question and also generating a proof graph that explains the answer. However, compositional reasoning is not always unique and there may be multiple ways of reaching the correct answer. Thus, in our work, we address a new and challenging problem of generating multiple proof graphs for reasoning over natural language rule-bases. Each proof provides a different rationale for the answer, thereby improving the interpretability of such reasoning systems. In order to jointly learn from all proof graphs and exploit the correlations between multiple proofs for a question, we pose this task as a set generation problem over structured output spaces where each proof is represented as a directed graph. We propose two variants of a proof-set generation model, multiPRover. Our first model, Multilabel-multiPRover, generates a set of proofs via multi-label classification and implicit conditioning between the proofs; while the second model, Iterative-multiPRover, generates proofs iteratively by explicitly conditioning on the previously generated proofs. Experiments on multiple synthetic, zero-shot, and human-paraphrased datasets reveal that both multiPRover models significantly outperform PRover on datasets containing multiple gold proofs. Iterative-multiPRover obtains state-of-the-art proof F1 in zero-shot scenarios where all examples have single correct proofs. It also generalizes better to questions requiring higher depths of reasoning where multiple proofs are more frequent.
Anthology ID:
2021.naacl-main.287
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3662–3677
Language:
URL:
https://aclanthology.org/2021.naacl-main.287
DOI:
10.18653/v1/2021.naacl-main.287
Bibkey:
Cite (ACL):
Swarnadeep Saha, Prateek Yadav, and Mohit Bansal. 2021. multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3662–3677, Online. Association for Computational Linguistics.
Cite (Informal):
multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning (Saha et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.287.pdf
Video:
 https://aclanthology.org/2021.naacl-main.287.mp4
Code
 swarnaHub/multiPRover