When is multitask learning effective? Semantic sequence prediction under varying data conditions
Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to determine its success. In this paper we evaluate a range of semantic sequence labeling tasks in a MTL setup. We examine different auxiliary tasks, amongst which a novel setup, and correlate their impact to data-dependent conditions. Our results show that MTL is not always effective, significant improvements are obtained only for 1 out of 5 tasks. When successful, auxiliary tasks with compact and more uniform label distributions are preferable.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning
Multitask deep learning has been applied to patient outcome prediction from text, taking clinical notes as input and training deep neural networks with a joint loss function of multiple tasks. However, the joint training…
PredictionMultitasking Inhibits Semantic Drift
When intelligent agents communicate to accomplish shared goals, how do these goals shape the agents' language? We study the dynamics of learning in latent language policies (LLPs), in which instructor agents generate nat…
Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction
Multimodal fusion and multitask learning are two vital topics in machine learning. Despite the fruitful progress, existing methods for both problems are still brittle to the same challenge -- it remains dilemmatic to int…
Semantic SegmentationPain Evaluation in Video using Extended Multitask Learning from Multidimensional Measurements
Previous work on automated pain detection from facial expressions has primarily focused on frame-level pain metrics based on specific facial muscle activations, such as Prkachin and Solomon Pain Intensity (PSPI). However…
Pain Intensity RegressionSemantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach
In recent years, the multimedia forensics and security community has seen remarkable progress in multitask learning for DeepFake (i.e., face forgery) detection. The prevailing approach has been to frame DeepFake detectio…
AttributeBinary ClassificationDeepFake DetectionFace Swapping