Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models

TL;DR

This paper introduces Text Modular Networks (TMNs), a framework for decomposing complex tasks into simpler, model-solvable sub-tasks using natural language, enhancing interpretability and robustness in question answering systems.

Contribution

The paper presents TMNs, a novel approach that learns to decompose tasks into sub-tasks in natural language, enabling interpretable reasoning without additional human annotations.

Findings

ModularQA outperforms existing explainable systems on DROP and HotpotQA.

TMNs improve robustness over blackbox models.

Generated explanations are more understandable and trustworthy.

Abstract

We propose a general framework called Text Modular Networks(TMNs) for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvable by existing models. To ensure solvability of simpler tasks, TMNs learn the textual input-output behavior (i.e., language) of existing models through their datasets. This differs from prior decomposition-based approaches which, besides being designed specifically for each complex task, produce decompositions independent of existing sub-models. Specifically, we focus on Question Answering (QA) and show how to train a next-question generator to sequentially produce sub-questions targeting appropriate sub-models, without additional human annotation. These sub-questions and answers provide a faithful natural language explanation of the model's reasoning. We use this framework to build ModularQA, a system that can answer multi-hop reasoning questions by decomposing them into sub-questions answerable by a neural factoid single-span QA model and a symbolic calculator. Our experiments show that ModularQA is more versatile than existing explainable systems for DROP and HotpotQA datasets, is more robust than state-of-the-art blackbox (uninterpretable) systems, and generates more understandable and trustworthy explanations compared to prior work.