# OPERA:Operation-Pivoted Discrete Reasoning over Text

arXiv: https://arxiv.org/abs/2204.14166 · HTML: https://mlsanity.com/paper/2204.14166/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 22 references that are in the map.
- First posted on arXiv 29 Apr 2022.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Injecting Numerical Reasoning Skills into Language Models](https://mlsanity.com/paper/2004.04487/) (2020)
- [NumNet: Machine Reading Comprehension with Numerical Reasoning](https://mlsanity.com/paper/1910.06701/) (2019)
- [Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension](https://mlsanity.com/paper/1909.00109/) (2019)
- [A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning](https://mlsanity.com/paper/1908.05514/) (2019)
- [Question Directed Graph Attention Network for Numerical Reasoning over Text](https://mlsanity.com/paper/2009.07448/) (2020)
- [RoR: Read-over-Read for Long Document Machine Reading Comprehension](https://mlsanity.com/paper/2109.04780/) (2021)
- [A Simple and Effective Model for Answering Multi-span Questions](https://mlsanity.com/paper/1909.13375/) (2019)
- [EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension](https://mlsanity.com/paper/2108.07994/) (2021)

## Built on by (most cited first, 7 of 7)

- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation](https://mlsanity.com/paper/2210.08249/) (2022)
- [DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2211.12668/) (2022)
- [MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering](https://mlsanity.com/paper/2210.10350/) (2022)
- [Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts](https://mlsanity.com/paper/2205.12496/) (2022)
- [Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering](https://mlsanity.com/paper/2306.04508/) (2023)
- [HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering over Heterogeneous Knowledge](https://mlsanity.com/paper/2308.11257/) (2023)

## Abstract (arXiv)

Machine reading comprehension (MRC) that requires discrete reasoning involving symbolic operations, e.g., addition, sorting, and counting, is a challenging task. According to this nature, semantic parsing-based methods predict interpretable but complex logical forms. However, logical form generation is nontrivial and even a little perturbation in a logical form will lead to wrong answers. To alleviate this issue, multi-predictor -based methods are proposed to directly predict different types of answers and achieve improvements. However, they ignore the utilization of symbolic operations and encounter a lack of reasoning ability and interpretability. To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability. Specifically, operations are first selected and then softly executed to simulate the answer reasoning procedure. Extensive experiments on both DROP and RACENum datasets show the reasoning ability of OPERA. Moreover, further analysis verifies its interpretability.