Please login to be able to save your searches and receive alerts for new content matching your search criteria.
These days, ELMo [3], BERT [1], BART [2] and other similarly cutely-named models appear to have dramatically advanced the state of the art in basically every problem in natural language processing and information retrieval. It can leave a researcher ...
With the rise of conversational assistants, it has become more critical for dialog systems to keep users engaged by responding in a natural, interesting, and often personalized way, even in a task-oriented setting. Recent work has thus focused on ...
In mobile edge computing (MEC), computation offloading is a promising way to support those resource-constrained mobile devices, since it moves some time-consuming computation activities to nearby edge servers. Owing to the geographical distribution of ...
Many of the challenges entailed in detecting online misinformation are related to our own cognitive limitations as human beings: We can only see a small part of the world at once, so we need to rely on others to pre-process part of that information for ...
Computer Vision Problems, such as object detection, object tracking, action recognition and so on, have been, in the past, usually addressed through Statistical Pattern Recognition techniques. SVM, Regression or Neural Networks, are some examples of ...
Text data is highly unstructured and can often be viewed as a complex representation of different concepts, entities, events, sentiments etc. For a wide variety of computational tasks, it is thus very important to annotate text data with the associated ...
Detecting and characterizing people with mental disorders is an important task that could help the work of different healthcare professionals. Sometimes, a diagnosis for specific mental disorders requires a long time, possibly causing problems because ...
We report goals, paper submissions, keynotes, and organizations of this UserNLP workshop. User-centered NLP can fill these gaps by explicitly considering stylistic variations across individuals or groups of individuals and focusing on user-level ...
In recent years, deep learning and web of things (WoT) have become hot topics. The relevant research issues in deep learning have been in increasingly investigated and published. Therefore, the title of this workshop is ”the 2nd International Workshop ...
SocialNLP is a new inter-disciplinary area of natural language processing (NLP) and social computing. We consider three plausible directions of SocialNLP: (1) addressing issues in social computing using NLP techniques; (2) solving NLP problems using ...
The First Workshop on Graph Learning aims to bring together researchers and practitioners from academia and industry to discuss recent advances and core challenges of graph learning. This workshop will be established as a platform for multiple ...
Expressing opinions and interacting with others on the Web has led to an abundance of online discourse: claims and viewpoints on controversial topics, their sources and contexts. This constitutes a valuable source of insights for studies into mis- / ...
The diffusion of the Internet of Things allows nowadays to sense human mobility in great detail, fostering human mobility studies and their applications in various contexts, from traffic management to public security and computational epidemiology. A ...
Recently, industrial recommendation services have been boosted by the continual upgrade of deep learning methods. However, they still face de-biasing challenges such as exposure bias and cold-start problem, where circulations of machine learning ...
We consider multi-label classification in the context of complex hierarchical relationships organized into an ontology. These situations are ubiquitous in learning problems on the web and in science, where rich domain models are developed but labeled ...
Semi-supervised and self-supervised learning on graphs are two popular avenues for graph representation learning. We demonstrate that no single method from semi-supervised and self-supervised learning works uniformly well for all settings in the node ...
Graph data structures are fundamental for studying connected entities. With an increase in the number of applications where data is represented as graphs, the problem of graph generation has recently become a hot topic. However, despite its ...
Entity Alignment (EA) is the task of recognizing the same entity present in different knowledge bases. Recently, embedding-based EA techniques have established dominance where alignment is done based on closeness in latent space. Graph Neural Networks (...
Training of Relational Graph Convolutional Networks (R-GCN) is a memory intense task. The amount of gradient information that needs to be stored during training for real-world graphs is often too large for the amount of memory available on most GPUs. ...
Graph Augmentation Learning (GAL) provides outstanding solutions for graph learning in handling incomplete data, noise data, etc. Numerous GAL methods have been proposed for graph-based applications such as social network analysis and traffic flow ...