# A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning

arXiv: https://arxiv.org/abs/1908.05514 · HTML: https://mlsanity.com/paper/1908.05514/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2019.

## Built on by (most cited first, 30 of 41)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Active Prompting with Chain-of-Thought for Large Language Models](https://mlsanity.com/paper/2302.12246/) (2023)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [Successive Prompting for Decomposing Complex Questions](https://mlsanity.com/paper/2212.04092/) (2022)
- [Towards Complex Document Understanding By Discrete Reasoning](https://mlsanity.com/paper/2207.11871/) (2022)
- [Reasoning Like Program Executors](https://mlsanity.com/paper/2201.11473/) (2022)
- [PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance](https://mlsanity.com/paper/2210.08817/) (2022)
- [Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models](https://mlsanity.com/paper/2304.11657/) (2023)
- [UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation](https://mlsanity.com/paper/2210.08249/) (2022)
- [Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks](https://mlsanity.com/paper/2304.01665/) (2023)
- [Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning](https://mlsanity.com/paper/2101.11802/) (2021)
- [What's in your Head? Emergent Behaviour in Multi-Task Transformer Models](https://mlsanity.com/paper/2104.06129/) (2021)
- [Numerical reasoning in machine reading comprehension tasks: are we there yet?](https://mlsanity.com/paper/2109.08207/) (2021)
- [OPERA:Operation-Pivoted Discrete Reasoning over Text](https://mlsanity.com/paper/2204.14166/) (2022)
- [Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems](https://mlsanity.com/paper/2210.05075/) (2022)
- [Paired Examples as Indirect Supervision in Latent Decision Models](https://mlsanity.com/paper/2104.01759/) (2021)
- [Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems](https://mlsanity.com/paper/2211.07455/) (2022)
- [Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering](https://mlsanity.com/paper/2212.10696/) (2022)
- [MarkQA: A large scale KBQA dataset with numerical reasoning](https://mlsanity.com/paper/2310.15517/) (2023)
- [Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs](https://mlsanity.com/paper/2305.01938/) (2023)
- [How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension](https://mlsanity.com/paper/2306.00435/) (2023)
- [NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering](https://mlsanity.com/paper/2211.03462/) (2022)
- [Development of an Extractive Clinical Question Answering Dataset with Multi-Answer and Multi-Focus Questions](https://mlsanity.com/paper/2201.02517/) (2022)
- [1Cademy @ Causal News Corpus 2022: Enhance Causal Span Detection via Beam-Search-based Position Selector](https://mlsanity.com/paper/2210.17157/) (2022)
- [EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension](https://mlsanity.com/paper/2108.07994/) (2021)
- [Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text](https://mlsanity.com/paper/2109.02289/) (2021)
- [Unsupervised Numerical Reasoning to Extract Phenotypes from Clinical Text by Leveraging External Knowledge](https://mlsanity.com/paper/2204.10202/) (2022)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)

## Abstract (arXiv)

Rapid progress has been made in the field of reading comprehension and question answering, where several systems have achieved human parity in some simplified settings. However, the performance of these models degrades significantly when they are applied to more realistic scenarios, such as answers involve various types, multiple text strings are correct answers, or discrete reasoning abilities are required. In this paper, we introduce the Multi-Type Multi-Span Network (MTMSN), a neural reading comprehension model that combines a multi-type answer predictor designed to support various answer types (e.g., span, count, negation, and arithmetic expression) with a multi-span extraction method for dynamically producing one or multiple text spans. In addition, an arithmetic expression reranking mechanism is proposed to rank expression candidates for further confirming the prediction. Experiments show that our model achieves 79.9 F1 on the DROP hidden test set, creating new state-of-the-art results. Source codefootnoteurlhttps://github.com/huminghao16/MTMSN is released to facilitate future work.