Related papers: Concept Based Continuous Prompts for Interpretable…

Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel…

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail -- by learning these…

We propose a novel prompt tuning method called CoAPT(Context Attribute words in Prompt Tuning) for few/zero-shot image classification. The core motivation is that attributes are descriptive words with rich information about a given concept.…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement…

Explainable Artificial Intelligence (XAI) poses a significant challenge in providing transparent and understandable insights into complex AI models. Traditional post-hoc algorithms, while useful, often struggle to deliver interpretable…

While the embedding of words has revolutionized the field of Natural Language Processing, the embedding of concepts has received much less attention so far. A dense and meaningful representation of concepts, however, could prove useful for…

Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their ``black-box'' nature poses challenges for responsible implementation. Although…

Topic modeling is a widely used technique for revealing underlying thematic structures within textual data. However, existing models have certain limitations, particularly when dealing with short text datasets that lack co-occurring words.…

Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…

Motivation: Phenotype concept recognition (CR) is a fundamental task in biomedical text mining. However, existing methods either require ontology-specific training, making them struggle to generalize across diverse text styles and evolving…

Continual learning (CL) has attracted increasing attention in the recent past. It aims to mimic the human ability to learn new concepts without catastrophic forgetting. While existing CL methods accomplish this to some extent, they are…

In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, combining distributional and lexical semantics in an…

Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system's ease of use, and gain users' trust. A typical approach to realize it is natural language…

Prompt learning for vision-language models, e.g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons. Existing prompt learning…

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

Advancements in foundation models (FMs) have led to a paradigm shift in machine learning. The rich, expressive feature representations from these pre-trained, large-scale FMs are leveraged for multiple downstream tasks, usually via…

Recent advances in open-vocabulary object detection models will enable Automatic Target Recognition systems to be sustainable and repurposed by non-technical end-users for a variety of applications or missions. New, and potentially nuanced,…

Word embeddings capture syntactic and semantic information about words. Definition modeling aims to make the semantic content in each embedding explicit, by outputting a natural language definition based on the embedding. However, existing…

Concept Bottleneck Models (CBMs) aim to enhance interpretability by predicting human-understandable concepts as intermediates for decision-making. However, these models often face challenges in ensuring reliable concept representations,…