Large language models (LLMs) have recently demonstrated state-of-the-art performance in various natural language processing (NLP) tasks, achieving near-human levels in multiple language understanding challenges and aligning closely with the core principles of semantic communication Inspired by LLMs’ advancements in semantic processing, we propose LLM-SC, an innovative LLM-enabled semantic communication system framework which applies LLMs directly to the physical layer coding and decoding for the first time. By analyzing the relationship between the training process of LLMs and the optimization objectives of semantic communication, we propose training a semantic encoder through LLMs’ tokenizer training and establishing a semantic knowledge base via the LLMs’ unsupervised pre-training process. This knowledge base facilitates the creation of optimal decoder by providing the prior probability of the transmitted language sequence. Based on this, we derive the optimal decoding criteria for the receiver and introduce beam search algorithm to further reduce complexity. Furthermore, we assert that existing LLMs can be employed directly for LLM-SC without extra re-training or fine-tuning. Simulation results reveal that LLM-SC outperforms conventional DeepSC at signal-to-noise ratios (SNRs) exceeding 3 dB, as it enables error-free transmissions of semantic information under high SNRs while DeepSC fails to do so. In addition to semantic-level performance, LLM-SC demonstrates compatibility with technical-level performance, achieving approximately an 8 dB coding gain for a bit error ratio (BER) of ${10}^{-3}$ without any channel coding while maintaining the same joint source–channel coding rate as traditional communication systems.

End-to-end relation extraction (E2ERE) generally performs named entity recognition and relation extraction either simultaneously or sequentially. While numerous studies on E2ERE have centered on enhancing span representations to improve model performance, challenges remain due to the gaps between subtasks (named entity recognition and relation extraction) and the modeling discrepancies between entities and relations. In this paper, we propose a novel Label Annotation Interaction-based representation enhancement method for E2ERE, which institutes a two-phase semantic interaction to augment representations. Specifically, we firstly feed label annotations that are easy to manually annotate into a language model, and conduct the first-round interaction between three types of tokens with a partial attention mechanism; Then we construct a latent multi-view graph to capture various possible links between label and entity (pair) nodes, facilitating the second-round interaction between entities and labels. A series of comparative experiments with methods of various transformer-based architectures currently in use show that LAI-Net can maintain performance on par with the current SOTA in terms of NER task, and achieves significant improvements over existing SOTA models in terms of RE task.

End-to-end relation extraction (E2ERE) generally performs named entity recognition and relation extraction either simultaneously or sequentially. While numerous studies on E2ERE have centered on enhancing span representations to improve model performance, challenges remain due to the gaps between subtasks (named entity recognition and relation extraction) and the modeling discrepancies between entities and relations. In this paper, we propose a novel Label Annotation Interaction based representation enhancement method for E2ERE, which institutes a two-phase semantic interaction to augment representations. Specifically, we firstly feed label annotations that are easy to manually annotate into a language model, and conduct the first round interaction between three types of tokens with a partial attention mechanism; Then construct a latent multi-view graph to capture various possible links between label and entity (pair) nodes, facilitating the second round interaction between entities and labels. A series of comparative experiments with methods of various transformer-based architectures currently in use have shown that LAI-Net can maintain performance on par with the current SOTA in terms of NER task, and achieves significant improvements over existing SOTA models in terms of RE task.

Under the wave of digital and intelligent transformation in education, Artificial Intelligence (AI) technology has exerted a profound impact on the structure and models of the current educational ecosystem. Taking the construction of machine learning courses in higher education as the starting point, this paper analyzes the key processes involved in curriculum construction and delves into how AI technology can empower the construction of such courses, thereby providing theoretical support for course design in the era of AI. Looking ahead, the integration of AI and education will continue to deepen, lending strong support to the cultivation of innovative talent and the building of a robust educational system.