Related papers: Concept Boundary Vectors
Concept learning is a form of supervised machine learning that operates on knowledge bases in description logics. State-of-the-art concept learners often rely on an iterative search through a countably infinite concept space. In each…
Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning (ICL) tasks that causally drive task performance. Across…
Word embedding models offer continuous vector representations that can capture rich contextual semantics based on their word co-occurrence patterns. While these word vectors can provide very effective features used in many NLP tasks such as…
Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene…
We present a novel method for using agent experiences gathered through an embodied simulation to ground contextualized word vectors to object representations. We use similarity learning to make comparisons between different object types…
Pre-trained language models (PLMs) have been prevailing in state-of-the-art methods for natural language processing, and knowledge-enhanced PLMs are further proposed to promote model performance in knowledge-intensive tasks. However,…
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…
Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and…
Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification. However, the annotation of concepts…
Conceptual spaces are geometric representations of conceptual knowledge, in which entities correspond to points, natural properties correspond to convex regions, and the dimensions of the space correspond to salient features. While…
We propose Concept Tokens, a lightweight method that adds a new special token to a pretrained LLM and learns only its embedding from multiple natural language definitions of a target concept, where occurrences of the concept are replaced by…
Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models…
Vector representation of sentences is important for many text processing tasks that involve clustering, classifying, or ranking sentences. Recently, distributed representation of sentences learned by neural models from unlabeled data has…
Existing research for image captioning usually represents an image using a scene graph with low-level facts (objects and relations) and fails to capture the high-level semantics. In this paper, we propose a Theme Concepts extended Image…
Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days. Among the range of different linguistic items, words have attracted the most…
Traditional deep learning interpretability methods which are suitable for model users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations…
Concept bottleneck models have been successfully used for explainable machine learning by encoding information within the model with a set of human-defined concepts. In the context of human-assisted or autonomous driving, explainability…
Current work on human-machine alignment aims at understanding machine-learned latent spaces and their correspondence to human representations. G{\"a}rdenfors' conceptual spaces is a prominent framework for understanding human…
This paper presents a computational model of concept learning using Bayesian inference for a grammatically structured hypothesis space, and test the model on multisensory (visual and haptics) recognition of 3D objects. The study is…
This article presents a concept-centric paradigm for building agents that can learn continually and reason flexibly. The concept-centric agent utilizes a vocabulary of neuro-symbolic concepts. These concepts, such as object, relation, and…