NormMark：一种用于社会文化规范发现的弱监督马尔可夫模型
NormMark: A Weakly Supervised Markov Model for Socio-cultural Norm Discovery
AI总结：
本文提出NormMark，一种弱监督概率生成式马尔可夫模型，通过对话历史条件下的离散与连续潜在变量捕获对话交互中的潜在特征，在规范标注有限的数据集上取得优于GPT3等现有方法的F1分数。
摘要：
规范是文化上公认的行为准则，可以集成到对话模型中，以生成适合社会文化语境的语句。现有的规范识别方法往往只关注对话的表层特征，而没有考虑对话内部的交互。为了解决这一问题，我们提出了NormMark，一种概率生成式马尔可夫模型，用于在整个对话过程中携带潜在特征。这些特征由以对话历史为条件的离散和连续潜在变量捕获，并提高了模型在规范识别方面的能力。该模型可以使用变分技术在弱标注数据上进行训练。在一个规范标注有限的数据集上，我们表明我们的方法取得了更高的F1分数，优于当前最先进的方法，包括GPT3。
英文摘要：
Norms, which are culturally accepted guidelines for behaviours, can be integrated into conversational models to generate utterances that are appropriate for the socio-cultural context. Existing methods for norm recognition tend to focus only on surface-level features of dialogues and do not take into account the interactions within a conversation. To address this issue, we propose NormMark, a probabilistic generative Markov model to carry the latent features throughout a dialogue. These features are captured by discrete and continuous latent variables conditioned on the conversation history, and improve the model's ability in norm recognition. The model is trainable on weakly annotated data using the variational technique. On a dataset with limited norm annotations, we show that our approach achieves higher F1 score, outperforming current state-of-the-art methods, including GPT3.
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。
