# Unifying Question Answering, Text Classification, and Regression via Span Extraction

Source: [Unifying Question Answering, Text Classification, and Regression via Span Extraction](<https://www.sota2.com/research/paper/68fa665e1e209131cea0fe13>)

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

Data updated: 2025-10-27T05:59:47.071Z

Authors: Nitish Shirish Keskar, Bryan McCann, Caiming Xiong, Richard Socher

Published: 2019-04-19T17:58:29.000Z

## Abstract

Even as pre-trained language encoders such as BERT are shared across many tasks, the output layers of question answering, text classification, and regression models are significantly different. Span decoders are frequently used for question answering, fixed-class, classification layers for text classification, and similarity-scoring layers for regression tasks, We show that this distinction is not necessary and that all three can be unified as span extraction. A unified, span-extraction approach leads to superior or comparable performance in supplementary supervised pre-trained, low-data, and multi-task learning experiments on several question answering, text classification, and regression benchmarks.

## 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/1904.09286>)

[PDF](<https://arxiv.org/pdf/1904.09286.pdf>)