# A Simple and Effective Model for Answering Multi-span Questions

arXiv: https://arxiv.org/abs/1909.13375 · HTML: https://mlsanity.com/paper/1909.13375/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2019.

## Built on by (most cited first, 13 of 13)

- [Towards Complex Document Understanding By Discrete Reasoning](https://mlsanity.com/paper/2207.11871/) (2022)
- [Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework](https://mlsanity.com/paper/2109.05897/) (2021)
- [LIQUID: A Framework for List Question Answering Dataset Generation](https://mlsanity.com/paper/2302.01691/) (2023)
- [MetaQA: Combining Expert Agents for Multi-Skill Question Answering](https://mlsanity.com/paper/2112.01922/) (2021)
- [Multi-Row, Multi-Span Distant Supervision For Table+Text Question](https://mlsanity.com/paper/2112.07337/) (2021)
- [SpEL: Structured Prediction for Entity Linking](https://mlsanity.com/paper/2310.14684/) (2023)
- [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)
- [Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering](https://mlsanity.com/paper/2306.04508/) (2023)
- [Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments](https://mlsanity.com/paper/2105.13959/) (2021)
- [ListReader: Extracting List-form Answers for Opinion Questions](https://mlsanity.com/paper/2110.11692/) (2021)
- [Adopting the Multi-answer Questioning Task with an Auxiliary Metric for Extreme Multi-label Text Classification Utilizing the Label Hierarchy](https://mlsanity.com/paper/2303.01064/) (2023)

## Abstract (arXiv)

Models for reading comprehension (RC) commonly restrict their output space to the set of all single contiguous spans from the input, in order to alleviate the learning problem and avoid the need for a model that generates text explicitly. However, forcing an answer to be a single span can be restrictive, and some recent datasets also include multi-span questions, i.e., questions whose answer is a set of non-contiguous spans in the text. Naturally, models that return single spans cannot answer these questions. In this work, we propose a simple architecture for answering multi-span questions by casting the task as a sequence tagging problem, namely, predicting for each input token whether it should be part of the output or not. Our model substantially improves performance on span extraction questions from DROP and Quoref by 9.9 and 5.5 EM points respectively.