Multilingual Dialogue Generation and Localization with Dialogue Act Scripting

ACL ARR 2025 May Submission5584 Authors

Abstract: Non-English dialogue datasets are scarce, and models are often trained or evaluated on translations of English-language dialogues, an approach which can introduce artifacts that reduce their naturalness and cultural appropriateness. This work proposes Dialogue Act Script (DAS), a structured framework for encoding, localizing, and generating multilingual dialogues from abstract intent representations. Rather than translating dialogue utterances directly, DAS enables the generation of new dialogues in the target language that are culturally and contextually appropriate. By using structured dialogue act representations, DAS supports flexible localization across languages, mitigating translationese and enabling more fluent, naturalistic conversations. Human evaluations across Italian, German, and Chinese show that DAS-generated dialogues consistently outperform those produced by both machine and human translators on measures of cultural relevance, coherence, and situational appropriateness.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: multilingual / low resource, conversational modeling

Contribution Types: NLP engineering experiment

Languages Studied: Italian, German, Chinese, English

Submission Number: 5584