Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text
Numerical reasoning skills are essential for complex question answering (CQA) over text. It requires opertaions including counting, comparison, addition and subtraction. A successful approach to CQA on text, Neural Module Networks (NMNs), follows the programmer-interpreter paradigm and leverages specialised modules to perform compositional reasoning. However, the NMNs framework does not consider the relationship between numbers and entities in both questions and paragraphs. We propose effective techniques to improve NMNs' numerical reasoning capabilities by making the interpreter question-aware and capturing the relationship between entities and numbers. On the same subset of the DROP dataset for CQA on text, experimental results show that our additions outperform the original NMNs by 3.0 points for the overall F1 score.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringSimilar Papers 제목 키워드 기반
Teaching Neural Module Networks to Do Arithmetic
Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks(NMNs), follow the programmer-interpreter frame…
Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models
Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions. This paper proposes a ne…
Data AugmentationKnowledge Base Question AnsweringQuestion AnsweringModularized Zero-shot VQA with Pre-trained Models
Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA). Our approach is motivated by a few observations. First,…
object-detectionObject DetectionQuestion AnsweringRelational Reasoning+2Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers
This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, th…
Decision MakingReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding t…
Fact VerificationQuestion AnsweringSemantic ParsingTable-based Fact Verification+2