Abstract
With the requirements of natural language applications, multi-task sequence labeling methods have some immediate benefits over the single-task sequence labeling methods. Recently, many state-of-the-art multi-task sequence labeling methods were proposed, while still many issues to be resolved including (C1) exploring a more general relationship between tasks, (C2) extracting the task-shared knowledge purely and (C3) merging the task-shared knowledge for each task appropriately. To address the above challenges, we propose MTAA, a symmetric multi-task sequence labeling model, which performs an arbitrary number of tasks simultaneously. Furthermore, MTAA extracts the shared knowledge among tasks by adversarial learning and integrates the proposed multi-representation fusion attention mechanism for merging feature representations. We evaluate MTAA on two widely used data sets: CoNLL2003 and OntoNotes5.0. Experimental results show that our proposed model outperforms the latest methods on the named entity recognition and the syntactic chunking task by a large margin, and achieves state-of-the-art results on the part-of-speech tagging task.
Original language | English (US) |
---|---|
Article number | 9153102 |
Pages (from-to) | 2476-2488 |
Number of pages | 13 |
Journal | IEEE/ACM Transactions on Audio Speech and Language Processing |
Volume | 28 |
DOIs | |
State | Published - 2020 |
Externally published | Yes |
Keywords
- Adversarial learning
- attention mechanism
- multi-task learning
- sequence labeling
ASJC Scopus subject areas
- Computer Science (miscellaneous)
- Acoustics and Ultrasonics
- Computational Mathematics
- Electrical and Electronic Engineering