arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.09658cs.AI
收藏

面向目标导向对话系统的自动意图提取与话语分类算法

Algorithms for automatic intents extraction and utterances classification for goal-oriented dialogue systems

Orenburg State University(奥伦堡国立大学)

Leonid Legashev, Alexander Shukhman, Vadim Badikov

AI总结:

本文提出目标导向对话系统脚本自动生成框架,比较基于 BERTopic、LDA 的意图提取及逻辑回归、BERT 的话语分类方法,实验表明 bert-base-uncased 表现最佳。

摘要:

自然语言处理领域的现代机器学习技术可用于自动生成目标导向对话系统的脚本。本文提出了一个用于研究目标导向对话系统脚本自动生成的通用框架,描述了一种预处理 JSON 格式对话数据集的方法。文中比较了两种基于 BERTopic 和潜在 Dirichlet 分配的用户意图提取方法,并比较了两种已实现的、用于对目标导向对话系统用户陈述进行分类的算法,它们分别基于逻辑回归和 BERT transformer 模型。与其他方法相比,使用 bert-base-uncased 模型的 BERT transformer 方法在 Precision(0.80)、F1-score(0.78)和 Matthews 相关系数(0.74)三项指标上均取得了更好的结果。

英文摘要:

Modern machine learning techniques in the natural language processing domain can be used to automatically generate scripts for goal-oriented dialogue systems. The current article presents a general framework for studying the automatic generation of scripts for goal-oriented dialogue systems. A method for preprocessing dialog data sets in JSON format is described. A comparison is made of two methods for extracting user intent based on BERTopic and latent Dirichlet allocation. A comparison has been made of two implemented algorithms for classifying statements of users of a goal-oriented dialogue system based on logistic regression and BERT transformer models. The BERT transformer approach using the bert-base-uncased model showed better results for the three metrics Precision (0.80), F1-score (0.78) and Matthews correlation coefficient (0.74) in comparison with other methods.

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。

↑