# MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension

Source: [MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension](<https://www.sota2.com/research/paper/68fa68701e209131cea1c405>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:38:00.142Z

Authors: Huaishao Luo, Yu Shi, Ming Gong, Linjun Shou, Tianrui Li

Published: 2020-09-29T23:53:50.000Z

## Abstract

Span extraction is an essential problem in machine reading comprehension. Most of the existing algorithms predict the start and end positions of an answer span in the given corresponding context by generating two probability vectors. In this paper, we propose a novel approach that extends the probability vector to a probability matrix. Such a matrix can cover more start-end position pairs. Precisely, to each possible start index, the method always generates an end probability vector. Besides, we propose a sampling-based training strategy to address the computational cost and memory issue in the matrix training phase. We evaluate our method on SQuAD 1.1 and three other question answering benchmarks. Leveraging the most competitive models BERT and BiDAF as the backbone, our proposed approach can get consistent improvements in all datasets, demonstrating the effectiveness of the proposed method.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2009.14348>)

[PDF](<https://arxiv.org/pdf/2009.14348.pdf>)
