WordDecipher: Enhancing Digital Workspace Communication with Explainable AI for Non-native English Speakers
Yuexi Chen, Zhicheng Liu
TL;DR
NNES face miscommunication risks in digital workspace writing due to cross-language expressions. WordDecipher combines an intention detector using LLM prompting with style-embedding-based intensity scoring, a user-guided rewriter that produces intent-aligned rewrites, and a nuance explainer that compares rewrites in content and style spaces. Leveraging pre-trained representations such as RoBERTa and LISA embeddings, the system provides interpretable, distance-based guidance to help NNES select the most appropriate phrasing. The approach offers a practical, explainable workflow to improve precision and confidence in high-stakes text-based communication for NNES, as demonstrated in a representative usage scenario.
Abstract
Non-native English speakers (NNES) face challenges in digital workspace communication (e.g., emails, Slack messages), often inadvertently translating expressions from their native languages, which can lead to awkward or incorrect usage. Current AI-assisted writing tools are equipped with fluency enhancement and rewriting suggestions; however, NNES may struggle to grasp the subtleties among various expressions, making it challenging to choose the one that accurately reflects their intent. Such challenges are exacerbated in high-stake text-based communications, where the absence of non-verbal cues heightens the risk of misinterpretation. By leveraging the latest advancements in large language models (LLM) and word embeddings, we propose WordDecipher, an explainable AI-assisted writing tool to enhance digital workspace communication for NNES. WordDecipher not only identifies the perceived social intentions detected in users' writing, but also generates rewriting suggestions aligned with users' intended messages, either numerically or by inferring from users' writing in their native language. Then, WordDecipher provides an overview of nuances to help NNES make selections. Through a usage scenario, we demonstrate how WordDecipher can significantly enhance an NNES's ability to communicate her request, showcasing its potential to transform workspace communication for NNES.