# Multi-Task Networks With Universe, Group, and Task Feature Learning

arXiv: https://arxiv.org/abs/1907.01791 · HTML: https://mlsanity.com/paper/1907.01791/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks](https://mlsanity.com/paper/2302.11074/) (2023)
- [Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning](https://mlsanity.com/paper/2412.08587/) (2024)
- [An Effective Non-Autoregressive Model for Spoken Language Understanding](https://mlsanity.com/paper/2108.07005/) (2021)
- [Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/2210.10227/) (2022)
- [A Result based Portable Framework for Spoken Language Understanding](https://mlsanity.com/paper/2103.06010/) (2021)
- [Capture Salient Historical Information: A Fast and Accurate Non-Autoregressive Model for Multi-turn Spoken Language Understanding](https://mlsanity.com/paper/2206.12209/) (2022)
- [Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System](https://mlsanity.com/paper/2106.04835/) (2021)
- [A survey of joint intent detection and slot-filling models in natural language understanding](https://mlsanity.com/paper/2101.08091/) (2021)
- [Tackling Multiple Tasks with One Single Learning Framework](https://mlsanity.com/paper/2206.06322/) (2022)
- [Spoken Language Understanding for Conversational AI: Recent Advances and Future Direction](https://mlsanity.com/paper/2212.10728/) (2022)

## Abstract (arXiv)

We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised information at the inter-task level and can be encoded into the model. We investigate two variants of neural network architectures that accomplish this, learning different feature spaces at the levels of individual tasks, task groups, as well as the universe of all tasks: (1) parallel architectures encode each input simultaneously into feature spaces at different levels; (2) serial architectures encode each input successively into feature spaces at different levels in the task hierarchy. We demonstrate the methods on natural language understanding (NLU) tasks, where a grouping of tasks into different task domains leads to improved performance on ATIS, Snips, and a large inhouse dataset.