SC-LSTM: Learning Task-Specific Representations in Multi-Task Learning for Sequence Labeling

Peng Lu (LPXD1101 <at> outlook (point) com)

RALI, DIRO

Le 22 mai 2019 à 11 h 30

Salle 3195, Pavillon André-Aisenstadt


Multi-task learning (MTL) has been studied recently for sequence labeling. Typically, auxiliary tasks are selected specifically in order to improve the performance of a target task. Jointly learning multiple tasks in a way that benefits all of them simultaneously can increase the utility of MTL. In order to do so, we propose a new LSTM cell which contains both shared parameters that can learn from all tasks, and task-specific parameters that can learn task specific information. We name it a Shared-Cell Long-Short Term Memory. Experimental results on three sequence labeling benchmarks (named-entity recognition, text chunking, and part-of-speech tagging) demonstrate the effectiveness of this new type of cell.


Pour recevoir les annonces hebdomadaires par courriel, visitez http://rali.iro.umontreal.ca/rali/?q=fr/node/1631

Liste des autres séminaires