@inproceedings{553e07eb28424c32b3687e13563a3e7e,
title = "QBERT: Generalist Model for Processing Questions",
abstract = "Using a single model across various tasks is beneficial for training and applying deep neural sequence models. We address the problem of developing generalist representations of text that can be used to perform a range of different tasks rather than being specialised to a single application. We focus on processing short questions and developing an embedding for these questions that is useful on a diverse set of problems, such as question topic classification, equivalent question recognition, and question answering. This paper introduces QBERT, a generalist model for processing questions. With QBERT, we demonstrate how we can train a multi-task network that performs all question-related tasks and has achieved similar performance compared to its corresponding single-task models.",
keywords = "Deep Learning, Multi-task Learning, Text Processing",
author = "Zhaozhen Xu and Nello Cristianini",
year = "2023",
month = apr,
day = "1",
doi = "10.1007/978-3-031-30047-9_37",
language = "English",
isbn = "9783031300462",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer",
pages = "472--483",
editor = "Bruno Cr{\'e}milleux and Sibylle Hess and Siegfried Nijssen",
booktitle = "Advances in Intelligent Data Analysis XXI - 21st International Symposium on Intelligent Data Analysis, IDA 2023, Proceedings",
note = "21st International Symposium on Intelligent Data Analysis, IDA 2022 ; Conference date: 12-04-2023 Through 14-04-2023",
}