相关论文: LiPCoT: Linear Predictive Coding based Tokenizer f…

Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-sequence-to-sequence autoencoder (SEQ^3), consisting of two…

From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label scarcity, learning useful representations for periodic tasks…

Large Language Models (LLMs) present significant challenges for deployment in energy-constrained environments due to their large model sizes and high inference latency. Spiking Neural Networks (SNNs), inspired by the sparse event-driven…

Large language models (LLMs) have emerged as promising tools for assisting in medical tasks, yet processing Electronic Health Records (EHRs) presents unique challenges due to their longitudinal nature. While LLMs' capabilities to perform…

Unsupervised/self-supervised representation learning in time series is critical since labeled samples are usually scarce in real-world scenarios. Existing approaches mainly leverage the contrastive learning framework, which automatically…

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

Recent advances in large language models (LLMs), such as ChatGPT, have showcased remarkable zero-shot performance across various NLP tasks. However, the potential of LLMs in personality detection, which involves identifying an individual's…

With the widespread of digital environments, reliable authentication and continuous access control has become crucial. It can minimize cyber attacks and prevent frauds, specially those associated with identity theft. A particular interest…

Narrative understanding requires multidimensional semantic structures. This study investigates whether BERT embeddings encode dimensions of fictional narrative semantics -- time, space, causality, and character. Using an LLM to accelerate…

Clinical interactions are initially recorded and documented in free text medical notes. ICD coding is the task of classifying and coding all diagnoses, symptoms and procedures associated with a patient's visit. The process is often manual…

This paper introduces LLT-ECG, a novel method for electrocardiogram (ECG) signal classification that leverages concepts from theoretical physics to automatically generate features from time series data. Unlike traditional deep learning…

Although LLMs have demonstrated remarkable capabilities in processing and generating textual data, their pre-trained vocabularies are ill-suited for capturing the nuanced temporal dynamics and patterns inherent in time series. The discrete,…

Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To address the challenging label-permutation issue, prior methods…

Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and…

In this work, the issue of Parkinson's disease (PD) diagnostics using non-invasive antemortem techniques was tackled. A deep learning approach for classification of raw speech recordings in patients with diagnosed PD was proposed. The core…

Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level…

Recent advancements in transformer-based models have greatly improved time series analysis, providing robust solutions for tasks such as forecasting, anomaly detection, and classification. A crucial element of these models is positional…

Large language models have transformed the comprehension and generation of natural language tasks, but they come with substantial memory and computational requirements. Quantization techniques have emerged as a promising avenue for…

End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to…

Time series forecasting plays a significant role in finance, energy, meteorology, and IoT applications. Recent studies have leveraged the generalization capabilities of large language models (LLMs) to adapt to time series forecasting,…