Multi-Task Learning for Sequence Tagging: An Empirical Study

Understand

We study three general multi-task learning (MTL) approaches on 11 sequence tagging tasks.

• Our extensive empirical results show that in about 50% of the cases, jointly learning all 11 tasks improves upon either independent or pairwise learning of the tasks.
• We also show that pairwise MTL can inform us what tasks can benefit others or what tasks can be benefited if they are learned jointly.
• In particular, we identify tasks that can always benefit others as well as tasks that can always be harmed by others.