DeepAI AI Chat
Log In Sign Up

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

10/15/2022
by   Yongwei Zhou, et al.
Harbin Institute of Technology
hit-mtlab.net
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/07/2022

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

Hybrid tabular-textual question answering (QA) requires reasoning from h...
12/10/2019

Neural Module Networks for Reasoning over Text

Answering compositional questions that require multiple steps of reasoni...
04/28/2020

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

Verifying the correctness of a textual statement requires not only seman...
04/15/2020

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

Existing question answering datasets focus on dealing with homogeneous i...
08/18/2021

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

Reasoning machine reading comprehension (R-MRC) aims to answer complex q...
09/06/2021

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

Numerical reasoning skills are essential for complex question answering ...
10/18/2022

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

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