相关论文: Mixture of LoRA Experts with Multi-Modal and Multi…

Large Language Models (LLMs) have achieved impressive performance across a wide range of applications. However, they often suffer from hallucinations in knowledge-intensive domains due to their reliance on static pretraining corpora. To…

Recent advancements in Generative AI have significantly improved the efficiency and adaptability of natural language processing (NLP) systems, particularly through Retrieval-Augmented Generation (RAG), Low-Rank Adaptation (LoRA), and…

In this paper, we consider the problem of automatic modulation classification with multiple sensors in the presence of unknown time offset, phase offset and received signal amplitude. We develop a novel hybrid maximum likelihood (HML)…

While large language models (LLM) have made impressive progress in natural language processing, it remains unclear how to utilize them in improving automatic speech recognition (ASR). In this work, we propose to train a single multilingual…

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…

The data and compute requirements of current language modeling technology pose challenges for the processing and analysis of low-resource languages. Declarative linguistic knowledge has the potential to partially bridge this data scarcity…

Speech Emotion Recognition (SER) is crucial for human-computer interaction but still remains a challenging problem because of two major obstacles: data scarcity and imbalance. Many datasets for SER are substantially imbalanced, where data…

Continual learning (CL), which requires the model to learn multiple tasks sequentially, is crucial for large language models (LLMs). Recently, low-rank adaptation~(LoRA), one of the most representative parameter-efficient fine-tuning (PEFT)…

The Word Error Rate (WER) is the common measure of accuracy for Automatic Speech Recognition (ASR). Transcripts are usually pre-processed by substituting specific characters to account for non-semantic differences. As a result of this…

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Evaluating the performance of Grammatical Error Correction (GEC) models has become increasingly challenging, as large language model (LLM)-based GEC systems often produce corrections that diverge from provided gold references. This…

Large-scale recommendations commonly adopt a multi-stage cascading ranking system paradigm to balance effectiveness and efficiency. Early Stage Ranking (ESR) systems utilize the "user-item decoupling" approach, where independently learned…

Grammatical Error Correction (GEC) is the task of correcting errorful sentences into grammatically correct, semantically consistent, and coherent sentences. Popular GEC models either use large-scale synthetic corpora or use a large number…

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

The expansion of instruction-tuning data has enabled foundation language models to exhibit improved instruction adherence and superior performance across diverse downstream tasks. Semantically-rich 3D human motion is being progressively…

Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students…

Automated Short Answer Scoring (ASAS) is a critical component in educational assessment. While traditional ASAS systems relied on rule-based algorithms or complex deep learning methods, recent advancements in Generative Language Models…

Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a significant forgetting…

Automatic reading aloud evaluation can provide valuable support to teachers by enabling more efficient scoring of reading exercises. However, research on reading evaluation systems and applications remains limited. We present a novel…

Large language models (LLMs) have shown impressive capabilities in natural language processing tasks, including dialogue generation. This research aims to conduct a novel comparative analysis of two prominent techniques, fine-tuning with…