面向口语人机对话中词汇对齐的稳定且个性化画像研究
Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
AI总结：
本研究针对人机对话中的词汇对齐问题，探讨了如何构建稳定且个性化的词汇画像，发现基于10分钟转录语音的紧凑画像在性能与数据效率上达到最佳平衡。
摘要：
词汇对齐是指说话者在对话过程中开始使用相似词汇的现象，这被认为有助于实现成功的沟通。然而，其在对话智能体中的实现仍待深入探索，尤其是考虑到大型语言模型（LLMs）的最新进展。作为迈向在人机对话中实现词汇对齐的第一步，本研究借鉴了个性化对话智能体的策略，探讨了构建稳定、个性化的词汇画像作为词汇对齐基础的方法。具体而言，我们改变了用于构建画像的转录口语数据量，以及每个词性（POS）类别中包含在画像里的条目数量，并使用召回率、覆盖率和余弦相似度指标评估了画像随时间变化的性能。结果表明，更小且更紧凑的画像能提供性能与数据效率的最佳平衡，该画像是基于10分钟转录语音构建的，其中包含5个形容词条目、5个连词条目，以及各10个副词、名词、代词和动词条目。总而言之，本研究为构建稳定、个性化的词汇画像提供了实用见解，兼顾了最低数据需求，这为对话智能体中的词汇对齐策略奠定了基础。
英文摘要：
Lexical alignment, where speakers start to use similar words across conversation, is known to contribute to successful communication. However, its implementation in conversational agents remains underexplored, particularly considering the recent advancements in large language models (LLMs). As a first step towards enabling lexical alignment in human-agent dialogue, this study draws on strategies for personalising conversational agents and investigates the construction of stable, personalised lexical profiles as a basis for lexical alignment. Specifically, we varied the amounts of transcribed spoken data used for construction as well as the number of items included in the profiles per part-of-speech (POS) category and evaluated profile performance across time using recall, coverage, and cosine similarity metrics. It was shown that smaller and more compact profiles, created after 10 min of transcribed speech containing 5 items for adjectives, 5 items for conjunctions, and 10 items for adverbs, nouns, pronouns, and verbs each, offered the best balance in both performance and data efficiency. In conclusion, this study offers practical insights into constructing stable, personalised lexical profiles, taking into account minimal data requirements, serving as a foundational step toward lexical alignment strategies in conversational agents.
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。
