Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
This addresses the underexplored implementation of lexical alignment in conversational agents, providing practical insights for developers, though it is incremental as a foundational step.
This study tackled the problem of constructing stable, personalized lexical profiles for enabling lexical alignment in conversational agents, finding that smaller, compact profiles based on 10 minutes of transcribed speech with specific item counts per part-of-speech category offered the best balance in performance and data efficiency.
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.