Pith. sign in

Meta-Learning Multi-task Communication

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

In this paper, we describe a general framework: Parameters Read-Write Networks (PRaWNs) to systematically analyze current neural models for multi-task learning, in which we find that existing models expect to disentangle features into different spaces while features learned in practice are still entangled in shared space, leaving potential hazards for other training or unseen tasks. We propose to alleviate this problem by incorporating an inductive bias into the process of multi-task learning, that each task can keep informed of not only the knowledge stored in other tasks but the way how other tasks maintain their knowledge. In practice, we achieve above inductive bias by allowing different tasks to communicate by passing both hidden variables and gradients explicitly. Experimentally, we evaluate proposed methods on three groups of tasks and two types of settings (\textsc{in-task} and \textsc{out-of-task}). Quantitative and qualitative results show their effectiveness.

fields

cs.CL 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

Exploring Domain Shift in Extractive Text Summarization

cs.CL · 2019-08-30 · conditional · novelty 6.0

Publication source acts as a domain in extractive summarization, and domain tags plus meta-learning reduce, but do not eliminate, the performance drop on unseen news outlets.

citing papers explorer

Showing 1 of 1 citing paper.

  • Exploring Domain Shift in Extractive Text Summarization cs.CL · 2019-08-30 · conditional · none · ref 27 · internal anchor

    Publication source acts as a domain in extractive summarization, and domain tags plus meta-learning reduce, but do not eliminate, the performance drop on unseen news outlets.