arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.08941cs.AIcs.LO
收藏

理解人类对话的自动交互式特定领域会话代理

Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs

UT Dallas(德克萨斯大学达拉斯分校);IBM T. J. Watson Research Center(IBM托马斯·J·沃森研究中心);Universidad Rey Juan Carlos(胡安·卡洛斯国王大学)

Yankai Zeng, Abhiramon Rajasekharan, Parth Padalkar, Kinjal Basu, Joaquín Arias, Gopal Gupta

摘要:

实现与机器的类人通信仍然是知识表示和推理以及自然语言处理领域的经典且具有挑战性的主题。这些大语言模型(LLM)依赖于模式匹配,而不是对句子语义的真正理解。因此,它们可能会产生不正确的响应。为了产生一个肯定正确的反应,一个人必须“理解”句子的语义。为了实现这种“理解”,可以说需要基于逻辑(常识)的推理方法,例如答案集编程(ASP)。在本文中,我们描述了AutoConclusion系统,利用LLM和ASP开发一个会话代理,可以真正“理解”人类对话在受限领域。AutoConclusion专注于一个特定的领域,根据用户的偏好为他们提供当地餐馆的建议。AutoConclusion将交互式地理解用户的话语,识别其中缺失的信息,并通过自然语言语句请求用户提供信息。一旦AutoConclusion确定已接收到所有信息,它将根据从人类用户获得的用户偏好计算餐厅推荐。AutoConclusion基于我们之前开发的STAR框架,它使用GPT-3将人类对话框转换为谓词,以捕获对话框句子的深层结构。这些谓词然后被输入到目标导向的(CASP)ASP系统,用于执行常识推理。据我们所知,AutoConclusion是第一个可以像人类一样真实对话的自动对话代理,并在真正理解人类话语的基础上为人类提供帮助。

英文摘要:

Achieving human-like communication with machines remains a classic, challenging topic in the field of Knowledge Representation and Reasoning and Natural Language Processing. These Large Language Models (LLMs) rely on pattern-matching rather than a true understanding of the semantic meaning of a sentence. As a result, they may generate incorrect responses. To generate an assuredly correct response, one has to "understand" the semantics of a sentence. To achieve this "understanding", logic-based (commonsense) reasoning methods such as Answer Set Programming (ASP) are arguably needed. In this paper, we describe the AutoConcierge system that leverages LLMs and ASP to develop a conversational agent that can truly "understand" human dialogs in restricted domains. AutoConcierge is focused on a specific domain-advising users about restaurants in their local area based on their preferences. AutoConcierge will interactively understand a user's utterances, identify the missing information in them, and request the user via a natural language sentence to provide it. Once AutoConcierge has determined that all the information has been received, it computes a restaurant recommendation based on the user-preferences it has acquired from the human user. AutoConcierge is based on our STAR framework developed earlier, which uses GPT-3 to convert human dialogs into predicates that capture the deep structure of the dialog's sentence. These predicates are then input into the goal-directed s(CASP) ASP system for performing commonsense reasoning. To the best of our knowledge, AutoConcierge is the first automated conversational agent that can realistically converse like a human and provide help to humans based on truly understanding human utterances.

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。

↑