Deep learning approaches have achieved great success in the field of Natural Language
Processing (NLP). However, directly training deep neural models often suffer from overfitting …

Designing magic shotgun compounds, ie, compounds hitting multiple targets using artificial
intelligence (AI) systems based on machine learning (ML) and deep learning (DL) …

Voice assistants are spreading in various environments, such as houses and cars, bringing
the possibility of controlling heterogeneous Internet of Things devices with simple voice …

To understand diverse natural language commands, virtual assistants today are trained with
numerous labor-intensive, manually annotated sentences. This paper presents a …

Different conflicting optimization criteria arise naturally in various Deep Learning scenarios.
These can address different main tasks (ie, in the setting of Multi-Task Learning), but also …

This paper introduces a meaning representation for spoken language understanding. The
Alexa meaning representation language (AMRL), unlike previous approaches, which factor …

Media technologies now provide facts, answers, and “knowledge” to people–search
engines, apps, and virtual assistants increasingly articulate responses rather than direct …

Classifying and segmenting skin cancer represent pivotal objectives for automated
diagnostic systems that utilize dermoscopy images. However, these tasks present significant …

Deep neural networks have been used for traffic classifications and promising results have
been obtained. However, most of the previous work confined to one specific task of the …

Building a question-answering agent currently requires large annotated datasets, which are
prohibitively expensive. This paper proposes Schema2QA, an open-source toolkit that can …