DeepAI AI Chat
Log In Sign Up

UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation

by   Yongwei Zhou, et al.
Harbin Institute of Technology

Question answering requiring discrete reasoning, e.g., arithmetic computing, comparison, and counting, over knowledge is a challenging task. In this paper, we propose UniRPG, a semantic-parsing-based approach advanced in interpretability and scalability, to perform unified discrete reasoning over heterogeneous knowledge resources, i.e., table and text, as program generation. Concretely, UniRPG consists of a neural programmer and a symbolic program executor, where a program is the composition of a set of pre-defined general atomic and higher-order operations and arguments extracted from table and text. First, the programmer parses a question into a program by generating operations and copying arguments, and then the executor derives answers from table and text based on the program. To alleviate the costly program annotation issue, we design a distant supervision approach for programmer learning, where pseudo programs are automatically constructed without annotated derivations. Extensive experiments on the TAT-QA dataset show that UniRPG achieves tremendous improvements and enhances interpretability and scalability compared with state-of-the-art methods, even without derivation annotation. Moreover, it achieves promising performance on the textual dataset DROP without derivations.


page 1

page 2

page 3

page 4


NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering

Hybrid tabular-textual question answering (QA) requires reasoning from h...

Neural Module Networks for Reasoning over Text

Answering compositional questions that require multiple steps of reasoni...

LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network

Verifying the correctness of a textual statement requires not only seman...

HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data

Existing question answering datasets focus on dealing with homogeneous i...

EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension

Reasoning machine reading comprehension (R-MRC) aims to answer complex q...

Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text

Numerical reasoning skills are essential for complex question answering ...

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

Numerical reasoning over text is a challenging task of Artificial Intell...