SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.00751 · NAACL · 2021

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

Ashish Sabharwal, Peter Clark, Daniel Khashabi, Tushar Khot, Kyle Richardson

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 submodels. Specifically, we focus on Question Answering (QA) and show how to train a next-question generator to sequentially produce sub-questions targeting appropriate submodels, 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, 1 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 Hot-potQA datasets, is more robust than stateof-the-art blackbox (uninterpretable) systems, and generates more understandable and trustworthy explanations compared to prior work.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2009.00751")
get_code_for_paper("2009.00751")
have("2009.00751")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2009.00751.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2009.00751.svg)](https://syntology.ai/paper/2009.00751)

Connect an agent — have() is free.