Related papers: BotTriNet: A Unified and Efficient Embedding for S…

At Pinterest, we utilize image embeddings throughout our search and recommendation systems to help our users navigate through visual content by powering experiences like browsing of related content and searching for exact products for…

Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many…

Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In…

End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains…

This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…

Social bots play a significant role in many online social networks (OSN) as they imitate human behavior. This fact raises difficult questions about their capabilities and potential risks. Given the recent advances in Generative AI (GenAI),…

Pair-based metric learning has been widely adopted to learn sentence embedding in many NLP tasks such as semantic text similarity due to its efficiency in computation. Most existing works employed a sequence encoder model and utilized…

In this paper, we study the problem of author identification under double-blind review setting, which is to identify potential authors given information of an anonymized paper. Different from existing approaches that rely heavily on feature…

With the increasing use of social media data for health-related research, the credibility of the information from this source has been questioned as the posts may originate from automated accounts or "bots". While automatic bot detection…

The rapid growth of technology has led to the creation of computing networks. The applications of the Internet of Things are becoming more and more visible with the expansion and development of sensors and the use of a series of equipment…

Text classification is a popular topic of natural language processing, which has currently attracted numerous research efforts worldwide. The significant increase of data in social media requires the vast attention of researchers to analyze…

Online shopping caters to the needs of millions of users daily. Search, recommendations, personalization have become essential building blocks for serving customer needs. Efficacy of such systems is dependent on a thorough understanding of…

Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these…

Community detection is the task of discovering groups of nodes sharing similar patterns within a network. With recent advancements in deep learning, methods utilizing graph representation learning and deep clustering have shown great…

Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…

Although deep pre-trained language models have shown promising benefit in a large set of industrial scenarios, including Click-Through-Rate (CTR) prediction, how to integrate pre-trained language models that handle only textual signals into…

Few-shot segmentation focuses on the generalization of models to segment unseen object instances with limited training samples. Although tremendous improvements have been achieved, existing methods are still constrained by two factors. (1)…

With the widespread online social networks, hate speeches are spreading faster and causing more damage than ever before. Existing hate speech detection methods have limitations in several aspects, such as handling data insufficiency,…

This work proposes a data driven learning model for the synthesis of keystroke biometric data. The proposed method is compared with two statistical approaches based on Universal and User-dependent models. These approaches are validated on…

This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT. For each task, we first replicate and…