Related papers: When to generate hedges in peer-tutoring interacti…

Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing…

Tracking mouse cursor movements can be used to predict user attention on heterogeneous page layouts like SERPs. So far, previous work has relied heavily on handcrafted features, which is a time-consuming approach that often requires domain…

Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.…

A critical decision point when training predictors using multiple studies is whether studies should be combined or treated separately. We compare two multi-study prediction approaches in the presence of potential heterogeneity in…

In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt sentences with largely varied semantics or grammatical…

Adaptively forecasting human behavior in social settings is an important step toward achieving Artificial General Intelligence. Most existing research in social forecasting has focused either on unfocused interactions, such as pedestrian…

Self-supervised learning has shown great success in Speech Recognition. However, it has been observed that finetuning all layers of the learned model leads to lower performance compared to resetting top layers. This phenomenon is attributed…

Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this…

Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of…

Both humans and large language models are able to learn language without explicit structural supervision. What inductive biases make this learning possible? We address this fundamental cognitive question by leveraging transformer language…

Humor is a natural and fundamental component of human interactions. When correctly applied, humor allows us to express thoughts and feelings conveniently and effectively, increasing interpersonal affection, likeability, and trust. However,…

Generative artificial intelligence (AI) has the potential to scale up personalized tutoring through large language models (LLMs). Recent AI tutors are adapted for the tutoring task by training or prompting LLMs to follow effective…

Machine teaching often involves the creation of an optimal (typically minimal) dataset to help a model (referred to as the `student') achieve specific goals given by a teacher. While abundant in the continuous domain, the studies on the…

This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or interactions between users in a social network. Our goal is to…

There is considerable interest in developing techniques for predicting human behavior, for instance to enable emerging contentious situations to be forecast or the nature of ongoing but hidden activities to be inferred. A promising approach…

The interactions between cells and the extracellular matrix are vital for the self-organisation of tissues. In this paper we present proof-of-concept to use machine learning tools to predict the role of this mechanobiology in the…

Network embedding methods aim at learning low-dimensional latent representation of nodes in a network. These representations can be used as features for a wide range of tasks on graphs such as classification, clustering, link prediction,…

Throughout the search process, the user's gaze on inspected SERPs and websites can reveal his or her search interests. Gaze behavior can be captured with eye tracking and described with word-eye-fixations. Word-eye-fixations contain the…

This paper investigates the application of machine learning (ML) techniques to enable intelligent systems to learn multi-party turn-taking models from dialogue logs. The specific ML task consists of determining who speaks next, after each…

Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning…