Related papers: Learning Evolved Combinatorial Symbols with a Neur…
In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…
My doctoral research focuses on understanding semantic knowledge in neural network models trained solely to predict natural language (referred to as language models, or LMs), by drawing on insights from the study of concepts and categories…
Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on large datasets indicate an over-reliance on shallow…
Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…
The iterated learning model is an agent model which simulates the transmission of of language from generation to generation. It is used to study how the language adapts to pressures imposed by transmission. In each iteration, a language…
Predictive coding is a message-passing framework initially developed to model information processing in the brain, and now also topic of research in machine learning due to some interesting properties. One of such properties is the natural…
We study the interpretability issue of task-oriented dialogue systems in this paper. Previously, most neural-based task-oriented dialogue systems employ an implicit reasoning strategy that makes the model predictions uninterpretable to…
Motivation: Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are…
Gradual argumentation frameworks represent arguments and their relationships in a weighted graph. Their graphical structure and intuitive semantics makes them a potentially interesting tool for interpretable machine learning. It has been…
Understanding human language has been a sub-challenge on the way of intelligent machines. The study of meaning in natural language processing (NLP) relies on the distributional hypothesis where language elements get meaning from the words…
Cognition and language seem closely related to the human cognitive process, although they have not been studied and investigated in detail. Our brain is too complex to fully comprehend the structures and connectivity, as well as its…
Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…
While many recent methods aim to unlearn or remove knowledge from pretrained models, seemingly erased knowledge often persists and can be recovered in various ways. Because large foundation models are far from interpretable, understanding…
Recent advances in self-supervised modeling of text and images open new opportunities for computational models of child language acquisition, which is believed to rely heavily on cross-modal signals. However, prior studies have been limited…
The recent successes of deep learning and deep reinforcement learning have firmly established their statuses as state-of-the-art artificial learning techniques. However, longstanding drawbacks of these approaches, such as their poor sample…
Analogical Reasoning problems challenge both connectionist and symbolic AI systems as these entail a combination of background knowledge, reasoning and pattern recognition. While symbolic systems ingest explicit domain knowledge and perform…
Symbolic regression is emerging as a promising machine learning method for learning succinct underlying interpretable mathematical expressions directly from data. Whereas it has been traditionally tackled with genetic programming, it has…
Recent work has attempted to characterize the structure of semantic memory and the search algorithms which, together, best approximate human patterns of search revealed in a semantic fluency task. There are a number of models that seek to…
In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models. We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via an augmented Graph…
The development of large language models (LLMs) is limited by a lack of explainability, the absence of a unifying theory, and prohibitive operational costs. We propose a neuro-theoretical framework for the emergence of intelligence in…