Related papers: Deep Unknown Intent Detection with Margin Loss
In this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear time-invariant dynamical systems, the topic of damping factor identification…
Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their…
Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…
The intentional creation and spread of disinformation poses a significant threat to public discourse. However, existing English datasets and research rarely address the intentionality behind the disinformation. This work presents MALINT,…
Controlling the style of natural language by disentangling the latent space is an important step towards interpretable machine learning. After the latent space is disentangled, the style of a sentence can be transformed by tuning the style…
Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether target knowledge is truly erased remains challenging. Existing output-level metrics fail to detect…
Multiple intent detection and slot filling are two fundamental and crucial tasks in spoken language understanding. Motivated by the fact that the two tasks are closely related, joint models that can detect intents and extract slots…
Non-intrusive Load Monitoring (NILM) is an established technique for effective and cost-efficient electricity consumption management. The method is used to estimate appliance-level power consumption from aggregated power measurements. This…
In this paper the problem of complex event detection in the continuous domain (i.e. events with unknown starting and ending locations) is addressed. Existing event detection methods are limited to features that are extracted from the local…
We present polynomial time and sample efficient algorithms for learning an unknown depth-2 feedforward neural network with general ReLU activations, under mild non-degeneracy assumptions. In particular, we consider learning an unknown…
Machine Unlearning aims to remove specific data from trained models, addressing growing privacy and ethical concerns. We provide a theoretical analysis of a simple and widely used method - gradient ascent - used to reverse the influence of…
Segmentation of retinal layers from Optical Coherence Tomography (OCT) volumes is a fundamental problem for any computer aided diagnostic algorithm development. This requires preprocessing steps such as denoising, region of interest…
Intent detection and slot filling are two main tasks in natural language understanding (NLU) for identifying users' needs from their utterances. These two tasks are highly related and often trained jointly. However, most previous works…
The most common mental disorders experienced by a person in daily life are depression and anxiety. Social stigma makes people with depression and anxiety neglected by their surroundings. Therefore, they turn to social media like Twitter for…
The growing prosperity of social networks has brought great challenges to the sentimental tendency mining of users. As more and more researchers pay attention to the sentimental tendency of online users, rich research results have been…
Social media has become a ubiquitous tool for connecting with others, staying updated with news, expressing opinions, and finding entertainment. However, understanding the intention behind social media posts remains challenging due to the…
Identifying patient cohorts from clinical notes in secondary electronic health records is a fundamental task in clinical information management. However, with the growing number of clinical notes, it becomes challenging to analyze the data…
Abnormal event detection is a challenging task that requires effectively handling intricate features of appearance and motion. In this paper, we present an approach of detecting anomalies in videos by learning a novel LSTM based…
Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to detect the open (unknown) intent without prior knowledge.…
We present a highly compact run-time monitoring approach for deep computer vision networks that extracts selected knowledge from only a few (down to merely two) hidden layers, yet can efficiently detect silent data corruption originating…