ECLM：基于意图链的实体级语言模型用于口语理解
ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent
AI总结：
针对口语理解中令牌级对齐和语义级关联难题，提出实体级语言模型ECLM，将槽填充转为实体识别并引入意图链，显著提升多意图识别性能。
摘要：
大型语言模型（LLMs）在语言生成和一般任务性能方面展示了令人印象深刻的能力。然而，它们应用于口语理解（SLU）仍然具有挑战性，特别是在令牌级任务中，LLMs的自回归特性常常导致对齐问题。它们还难以通过直接微调来捕捉语义级任务中细微的相互关系。为了解决这些挑战，我们提出了实体级语言模型（ECLM）框架，该框架将槽填充重新表述为实体识别任务，并引入了一个新概念，即“意图链”，以实现逐步的多意图识别。实验结果表明，ECLM显著优于强基线如Uni-MIS，在MixATIS上取得了3.7%的提升，在MixSNIPS上取得了3.1%的提升。与LLMs的标准监督微调相比，ECLM在这些数据集上进一步实现了8.5%和21.2%的改进。我们的代码可在https://github.com/SJY8460/ECLM获取。
英文摘要：
Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level tasks, where the autoregressive nature of LLMs often leads to misalignment issues. They also struggle to capture nuanced interrelations in semantic-level tasks through direct fine-tuning alone. To address these challenges, we propose the Entity-level Language Model (ECLM) framework, which reformulates slot-filling as an entity recognition task and introduces a novel concept, \textit{Chain of Intent}, to enable step-by-step multi-intent recognition. Experimental results show that ECLM significantly outperforms strong baselines such as Uni-MIS, achieving gains of 3.7\% on MixATIS and 3.1\% on MixSNIPS. Compared to standard supervised fine-tuning of LLMs, ECLM further achieves improvements of 8.5\% and 21.2\% on these datasets, respectively. Our code is available at https://github.com/SJY8460/ECLM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
