paper-with-me

홈 › Papers

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

2020-09-01 · NAACL 2021 4 · Tushar Khot, Daniel Khashabi, Kyle Richardson, Peter Clark, Ashish Sabharwal

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.

📄 PDF Abstract BibTeX arXiv:2009.00751

Code (1)

allenai/modularqa 공식 구현

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Decomposed Prompting: A Modular Approach for Solving Complex Tasks

2022-10-05 · Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu 외

Few-shot prompting is a surprisingly powerful way to use Large Language Models (LLMs) to solve various tasks. However, this approach struggles as the task complexity increases or when the individual reasoning steps of th…

Information RetrievalRetrieval

Modular Networks: Learning to Decompose Neural Computation

2018-11-13 · NeurIPS 2018 12 · Louis Kirsch, Julius Kunze, David Barber

Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to…

DiversityLanguage ModelingLanguage Modelling

Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs

2024-08-12 · Chuanneng Sun, Songjun Huang, Dario Pompili

Large Language Models (LLMs) have demonstrated remarkable abilities in various language tasks, making them promising candidates for decision-making in robotics. Inspired by Hierarchical Reinforcement Learning (HRL), we p…

Decision MakingHierarchical Reinforcement LearningIn-Context LearningIn-Context Reinforcement Learning+4

OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning

2023-10-28 · Rim Assouel, Pau Rodriguez, Perouz Taslakian, David Vazquez 외

A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios. Such capacity is not yet attained for machine learning systems. In this work, in…

Data AugmentationOut-of-Distribution GeneralizationVisual Reasoning

Semantic Decomposition of Question and SQL for Text-to-SQL Parsing

2023-10-20 · Ben Eyal, Amir Bachar, Ophir Haroche, Moran Mahabi 외

Text-to-SQL semantic parsing faces challenges in generalizing to cross-domain and complex queries. Recent research has employed a question decomposition strategy to enhance the parsing of complex SQL queries. However, th…

RetrievalSemantic ParsingSQL ParsingText to SQL+1