Gated Task Interaction Framework for Multi-task Sequence Tagging

TL;DR

This paper introduces the Gated Tasks Interaction (GTI) framework, a multi-task learning approach that leverages neural gate modules to improve sequence tagging performance by modeling task relations.

Contribution

The paper proposes a novel GTI network that jointly learns linguistic features and sequence tagging tasks, effectively controlling information flow between tasks.

Findings

GTI outperforms baseline models on chunking and NER datasets.

Neural gate modules effectively model task relations.

Joint learning improves overall tagging accuracy.

Abstract

Recent studies have shown that neural models can achieve high performance on several sequence labelling/tagging problems without the explicit use of linguistic features such as part-of-speech (POS) tags. These models are trained only using the character-level and the word embedding vectors as inputs. Others have shown that linguistic features can improve the performance of neural models on tasks such as chunking and named entity recognition (NER). However, the change in performance depends on the degree of semantic relatedness between the linguistic features and the target task; in some instances, linguistic features can have a negative impact on performance. This paper presents an approach to jointly learn these linguistic features along with the target sequence labelling tasks with a new multi-task learning (MTL) framework called Gated Tasks Interaction (GTI) network for solving multiple sequence tagging tasks. The GTI network exploits the relations between the multiple tasks via neural gate modules. These gate modules control the flow of information between the different tasks. Experiments on benchmark datasets for chunking and NER show that our framework outperforms other competitive baselines trained with and without external training resources.