JPIS：一种基于用户画像的意图检测与槽填充联合模型，配备槽到意图注意力机制
JPIS: A Joint Model for Profile-based Intent Detection and Slot Filling with Slot-to-Intent Attention
AI总结：
针对基于用户画像的意图检测与槽填充研究不足的问题，提出联合模型JPIS，融合画像信息并引入槽到意图注意力机制，在中文基准数据集ProSLU上取得最优整体准确率。
摘要：
基于用户画像的意图检测和槽填充是利用用户专属的支撑画像信息减少用户话语歧义的重要任务，但目前针对这两项任务的研究尚未得到广泛探索。为填补这一空白，我们提出了名为JPIS的联合模型，旨在增强基于画像的意图检测和槽填充效果。JPIS将支撑画像信息融入其编码器，并引入槽到意图注意力机制，将槽信息表示传递给意图检测模块。实验结果表明，我们的JPIS大幅优于以往的基于画像的模型，在中文基准数据集ProSLU上的整体准确率创下了新的SOTA（ state-of-the-art，最优）性能。
英文摘要：
Profile-based intent detection and slot filling are important tasks aimed at reducing the ambiguity in user utterances by leveraging user-specific supporting profile information. However, research in these two tasks has not been extensively explored. To fill this gap, we propose a joint model, namely JPIS, designed to enhance profile-based intent detection and slot filling. JPIS incorporates the supporting profile information into its encoder and introduces a slot-to-intent attention mechanism to transfer slot information representations to intent detection. Experimental results show that our JPIS substantially outperforms previous profile-based models, establishing a new state-of-the-art performance in overall accuracy on the Chinese benchmark dataset ProSLU.
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。
