Skip to content
#generative ai Open access

Integrating Corpus-Based Translation, Data-Driven Learning, and Generative AI for Professional Email Writing in ESP

Sep 2026 · Digital Studies in Language and Literature · 0 citations · 24 references

TL;DR

A didactic sequence designed to help (future) librarians develop professional email writing skills, with a focus on genre awareness and task-specific vocabulary, supported the development of genre-aware professional email writing while fostering transferable corpus-informed and AI-mediated writing strategies to new professional communication contexts.

Abstract

Abstract Professional communication in English has become increasingly important for librarians participating in international academic and institutional networks. However, many librarians and students have limited English proficiency and need support to write appropriate professional messages. This paper proposes and analyses a didactic sequence designed to help (future) librarians develop professional email writing skills, with a focus on genre awareness and task-specific vocabulary. The sequence emphasises interactional processes central to Data-driven Learning (DDL). Learner–corpus interactions involve building and exploring bilingual email corpora with generative Artificial Intelligence (AI) support, using concordance tools and query logs to identify recurring language patterns and genre conventions. Learner–AI interactions occur as participants use prompts, receive automated feedback, and compare AI-generated suggestions with their own drafts to refine accuracy and register. Peer–peer interactions are fostered through collaborative drafting and discussion activities. The study is framed by DDL and AI, Translation Studies and English for Specific Purposes. Implemented in a Librarianship course at a Brazilian public university, the sequence supported the development of genre-aware professional email writing while fostering transferable corpus-informed and AI-mediated writing strategies to new professional communication contexts.

Read PDF

Similar papers

Review Open access Sep 2026

From Chalk to Code: Transforming English Language Teaching Through AI-Integrated, Learner-Centric Pedagogy

Artificial intelligence is transforming English language teaching by introducing new possibilities for personalised instruction, automated feedback, conversational practice and learner-controlled language development. However, the integration of AI into English language teaching remains uneven, with existing research o...

K. Vijitha, Yogesh Babu Thunga · 0 citations
Open access Sep 2026

Trace Data of Secondary Students and Linguistic Analysis to Predict Learner Performance in a Multi‐Text Writing Task

Writing from multiple sources is a cognitively demanding task that requires students to integrate reading, planning, and composition processes. While prior research has demonstrated the importance of self‐regulated learning (SRL) and linguistic features in predicting writing performance, most studies have focused...

Halima Alnashiri, Mladen Raković, Sadia Nawaz et al. · 0 citations
Open access Aug 2026

Evaluating Grammarly-Assisted Post-Editing of Google Translate Outputs in Indonesian-English Academic Texts: An Exploratory Corpus Study with Expert Assessment

Background: This mixed-method study investigates the effectiveness of integrating Google Translate (GT) and Grammarly as a combined English-for-Academic-Purposes (EAP) learning and teaching intervention, aiming to improve the accuracy, clarity, and readability of Indonesian-to-English academic texts. Methodology: Th...

Ismiyati Hasiru, Novriyanto Napu, Suleman Bouti · 0 citations
Open access Aug 2026

Reading Representation with a Corpus: Critical Language Awareness Through Data-Driven Learning

The need for two skills that are not usually taught together has been growing in the field of language learning: critical language awareness (the capacity to analyse the ways in which texts shape identity and ideology) and corpus literacy (the capacity to investigate patterns of language with digital tools). Materials...

B. Pervaiz, Muhammad Azidan bin Abdul Jabar, Wan Muhammad bin Wan Sulong · 0 citations

Related blog posts

Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.