Multi-task Approach
Related Papers
Joint Estimation and Analysis of Risk Behavior Ratings in Movie Scripts
AbstractExposure to violent, sexual, or substance-abuse content in media increases the willingness of children and adolescents to imitate similar behaviors. Computational methods that identify portrayals of risk behaviors from audio-visual …...
Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification
AbstractSexism, a form of oppression based on one’s sex, manifests itself in numerous ways and causes enormous suffering. In view of the growing number of experiences of sexism reported online, …...
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information
Neural biomedical named entity recognition (BioNER) methods usually require a large amount of annotated data, while the anno- tated BioNER datasets are often difficult to obtain and small in scale …...
Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations
AbstractMajority voting and averaging are common approaches used to resolve annotator disagreements and derive single ground truth labels from multiple annotations. However, annotators may systematically disagree with one another, often …...
A New Direction in Stance Detection: Target-Stance Extraction in the Wild
AbstractStance detection aims to detect the stance toward a corresponding target. Existing works use the assumption that the target is known in advance, which is often not the case in …...
Conclusion-based Counter-Argument Generation
AbstractIn real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion. Existing work on the automatic generation of natural …...