--- title: "DeMINT — paper by Esplà-Gomis et al. (2025)" description: "DeMINT is a prototype conversational tutor for non-native English speakers. 3 references." authors: ["Miquel Esplà-Gomis", "Felipe Sánchez-Martínez", "Víctor M. Sánchez-Cartagena", "Juan Antonio Pérez-Ortiz"] year: 2025 venue: "Proceedings of Machine Translation Summit XX: Volume 2" source: "https://aclanthology.org/2025.mtsummit-2.18/" licence: "CC BY-ND 4.0 (stated in the PDF)" licence_url: "https://creativecommons.org/licenses/by-nd/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/gomis-2025-demint-automated-language-debriefing-english/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gomis-2025-demint-automated-language-debriefing-english/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/17/) / DeMINT: Automated Language Debriefing for English Learners via AI Chatbot Analysis of Meeting Transcripts # DeMINT: Automated Language Debriefing for English Learners via AI Chatbot Analysis of Meeting Transcripts **Authors:** [Miquel Esplà-Gomis](https://md.research.elamur.ai/free/en/authors/miquel-espla-gomis/), [Felipe Sánchez-Martínez](https://md.research.elamur.ai/free/en/authors/felipe-sanchez-martinez/), [Víctor M. Sánchez-Cartagena](https://md.research.elamur.ai/free/en/authors/victor-m-sanchez-cartagena/) and [Juan Antonio Pérez-Ortiz](https://md.research.elamur.ai/free/en/authors/juan-antonio-perez-ortiz/) · **Year:** 2025 · **Venue:** [Proceedings of Machine Translation Summit XX: Volume 2](https://md.research.elamur.ai/free/en/venues/mtsummit/) ([Machine Translation Summit (MT Summit) 2025](https://md.research.elamur.ai/free/en/venues/mtsummit/2025/)) · **Publisher:** [European Association for Machine Translation](https://md.research.elamur.ai/free/en/publishers/european-association-for-machine-translation/) · **Licence:** [CC BY-ND 4.0 (stated in the PDF)](https://creativecommons.org/licenses/by-nd/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2025.mtsummit-2.18/) · [PDF](https://aclanthology.org/2025.mtsummit-2.18.pdf) ## Summary DeMINT is a prototype conversational tutor for non-native English speakers. It reviews recordings of video meetings the learners took part in and then talks with each learner about the language mistakes they made. The system is a modular pipeline: - pyannote.audio splits the audio by speaker. - A Whisper model, adapted on spoken sentences that contain grammatical errors, transcribes the speech. - A T5 model trained on JF-LEG proposes corrections. - ERRANT labels the edits between the original and corrected sentences. - An LLM turns those labels into detailed explanations, using a few examples in the prompt. - Retrieval from English textbooks adds supporting material. - A fine-tuned Llama-3.1-8B suggests an empathetic teaching stance. - A Python orchestrator assembles all of this into a prompt, and GPT-4 writes the tutor's next turn. The evaluation was small: seven Spanish-speaking B2/C1 learners used the system after 15 recorded calls. They enjoyed it and wanted similar tools in the future. Their main complaints were the tutor's fluency and how reliably it detected errors. The work shows how standard MT-adjacent components can be combined into a personalised, error-driven tutor. ## Key points - Built by the Transducens group at Universitat d'Alacant (January–September 2024), funded through the UTTER project under Horizon Europe (GA 101,070,631). - Components: - pyannote.audio for diarization - fine-tuned Whisper for speech recognition - T5 fine-tuned on JF-LEG for grammatical error correction - ERRANT for edit annotation - RAG over textbooks for supporting material - Llama-3.1-8B trained on teacher–student dialogues for empathetic guidance - GPT-4 for generating the tutor's next turn - The evaluation involved 7 L1-Spanish learners at B2/C1, 15 video calls and roughly 75 minutes of chatbot interaction, with answers collected on a 1–5 Likert survey. - Every participant rated enjoyment 4 or 5, and five of seven gave a 4 for helping their English. Six of seven rated interest in future use 4 or 5. - Fluency and error-detection accuracy were the weakest aspects, both averaging 3. ## Interesting ideas - The speech recognizer is fine-tuned on utterances that contain grammatical errors, so it records what the learner actually said instead of silently fixing it. - Errors are found by correcting a sentence first and then diffing the original against the correction with ERRANT, which yields typed edits rather than an opaque rewrite. - The LLM only verbalises errors that a symbolic tool has already labelled, so its explanations stay anchored to structured annotations. - A deterministic orchestrator walks through the errors and builds the prompt, while a separate small model advises only on tone and teaching approach. - Learners named error-detection accuracy as the factor that most limited trust in the tutor. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (tokens): The tokenizer and tagger could be trained or tested on deliberately ungrammatical text so they keep learner errors visible instead of normalising them away. - **I2** (learn): When a self-induced repair rule changes a parse, Mova could diff the tree before and after the repair to log a typed, explainable edit category. - **I3** (back): Generation could follow the same split, with the meaning graph fixing what to say and a language model only choosing the wording, which keeps the output traceable. - **I4** (answer): Mova's tutoring "students" could keep content selection in explicit code and treat style or empathy as a separate, swappable advisory layer. - **I5** (learn): Evaluation should measure detection precision of the upstream analysis separately from end-user satisfaction, since a weak detector undermines everything built on top of it. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works 🧭 Topics (2): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works · [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 654 works ## Cite Cite as: Miquel Esplà-Gomis, Felipe Sánchez-Martínez, Víctor M. Sánchez-Cartagena and Juan Antonio Pérez-Ortiz. 2025. DeMINT: Automated Language Debriefing for English Learners via AI Chatbot Analysis of Meeting Transcripts. Proceedings of Machine Translation Summit XX: Volume 2. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{esplagomis2025demint, title = {{DeMINT: Automated Language Debriefing for English Learners via AI Chatbot Analysis of Meeting Transcripts}}, author = {Miquel Esplà-Gomis, Felipe Sánchez-Martínez, Víctor M. Sánchez-Cartagena and Juan Antonio Pérez-Ortiz}, booktitle = {Proceedings of Machine Translation Summit XX: Volume 2}, year = {2025}, url = {https://aclanthology.org/2025.mtsummit-2.18/} } ``` - [← previous DeformAr: Rethinking NER Evaluation through Component Analysis and Visual Analytics](https://md.research.elamur.ai/free/en/papers/younes-2025-deformar-rethinking-ner-evaluation-through/) - [next → Detecting terminologisation in nouns](https://md.research.elamur.ai/free/en/papers/ahumada-2025-detecting-terminologisation-nouns/) - [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/17/) ## References 3 references, 3 of them with a card of ours. ↗ leads to the work. 1. Christopher Bryant, Mariano Felice, and Ted Briscoe. 2017. [Automatic annotation and evaluation of error types for grammatical error correction](https://md.research.elamur.ai/free/en/papers/bryant-2017-automatic-annotation-evaluation-error-types/). In Proceedings of the 55th ACL Conference (Volume 1), pages 793–805, Vancouver, Canada. 2. Juan Antonio Pérez-Ortiz, Miquel Esplà-Gomis, Víctor M. Sánchez-Cartagena, Felipe Sánchez-Martínez, Roman Chernysh, Gabriel Mora-Rodríguez, and Lev Berezhnoy. 2024. [A conversational intelligent tutoring system for improving English proficiency of non-native speakers via debriefing of online meeting transcriptions](https://md.research.elamur.ai/free/en/papers/ortiz-2024-conversational-intelligent-tutoring-system-improving/). In Proceedings of the 13th Workshop NLP4CALL, pages 187–198, Rennes, France. 3. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of Machine Learning Research, 21(140):1–67. [↗](https://doi.org/10.48550/arxiv.1910.10683) *Updated 1 November 2026*