Elamur Research⌕
☰
home / papers / 2022 / Using NLP to Support English Teaching in Rural Schools

Using NLP to Support English Teaching in Rural Schools

Paper · 2022 · Luis Chiruzzo, Laura Musto, Santiago Gongora et al.

Summary

The paper reports on CINACINA, an ongoing Uruguayan research and university-extension project. It helps primary-school teachers in rural areas run English-as-a-foreign-language lessons. Many of these teachers are not fluent in English and work with poor or no Internet access. The team built a lightweight web application where teachers can assemble interactive activities around a topic or text. These include crosswords, word searches, a memory game, a story game, a language practice game and Sea Animals, a battleship-style multiplayer game for oral practice. Behind the games is a database of <word, definition> pairs, which can be entered by hand or extracted automatically. Teachers can correct errors made by the NLP components. The project grew from a 2016 crossword-from-news prototype through school-tested prototypes to a unified platform. The main lesson from field visits was that users first needed simpler, curated, beginner-level content rather than heavy automatic processing. More NLP features can follow once the basics are trusted. The work shows how to make NLP useful to underserved classrooms.

Key points

  • Context: about 60% of Uruguay's 1040 rural schools lack stable connectivity or physical access for English teachers. A 2018 program lets classroom teachers learn alongside pupils with remote specialist support. It now covers over half of rural schools and 42 special-needs schools.
  • Prototypes were tried in three rural schools in 2018. The exercises turned out too hard, and the tools were too raw to use without help.
  • In 2021, ANII funding paid for a web developer to merge the separate prototypes into one platform. The platform has three user roles: student, teacher and superuser.
  • The code is planned for release under CC BY-NC-SA 4.0 once a stable version exists.
  • Planned work includes:
    • integrating a QA generator for reading comprehension;
    • using BookNLP for the story game;
    • ordering story events chronologically rather than in narrative order;
    • a Timeline-style multiplayer mode;
    • automatic correction of errors typical of Spanish-speaking learners.

Interesting ideas

  • I1. The platform lets teachers quickly fix mistakes made by the automatic tools, so imperfect NLP output still becomes usable material and every fix is captured.
  • I2. The authors propose having the story game recover the true chronological order of events instead of the order in which the text tells them.
  • I3. They suggest a competitive game where players place story events in the correct sequence, modeled on the Timeline board game.
  • I4. Crosswords are built from automatically extracted <word, definition> pairs, turning a text into short gloss-style clues.
  • I5. Field visits showed the content was pitched too high, so the team simplified it to beginner level before adding more automation.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): Teacher or user corrections to Mova's outputs could be logged as gold repairs and fed into training or self-induced repair rules.
  • I2 (world): This is a natural test of Mova's event-ordering layer: compare narrative order with the inferred timeline and explain each reordering.
  • I3 (answer): Shuffled-event ordering items from fables and tales could become a school-style test type that checks Mova's understanding of temporal structure.
  • I4 (back): Generating a concise definition clue from a concept node in the meaning graph would be a compact exercise for the graph-to-text generator.
  • I5 (answer): Mova's student readers should be evaluated on graded tests at several difficulty levels, so a mismatch between system ability and task level shows up early.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Universidad de la República de UruguayMontevideo · Uruguay9 works · 450 citations

Also on the byline: Indiana University of Pennsylvania.

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksInformation Systems · 1,437 worksPsychology · 1,552 worksDevelopmental and Educational Psychology · 499 works

🧭 Topics 1Research subjects and languages the work is about.English · 2,263 works

Cite

Cite as Luis Chiruzzo, Laura Musto, Santiago Gongora, Brian Carpenter, Juan Filevich and Aiala Rosa. 2022. Using NLP to Support English Teaching in Rural Schools. Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.nlp4pi-1.13

@inproceedings{chiruzzo2022using,
  title = {{Using NLP to Support English Teaching in Rural Schools}},
  author = {Luis Chiruzzo, Laura Musto, Santiago Gongora, Brian Carpenter, Juan Filevich and Aiala Rosa},
  booktitle = {Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)},
  year = {2022},
  doi = {10.18653/v1/2022.nlp4pi-1.13},
  url = {https://doi.org/10.18653/v1/2022.nlp4pi-1.13}
}

References

17 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Manex Agirrezabal, Begoña Altuna, Lara Gil Vallejo, Josu Goikoetxea, and Itziar Gonzalez Dios. 2019. Creating vocabulary exercises through nlp. Digital Humanities in the Nordic Countries. Proceedings, 2019. ↗
  2. Rodrigo Arocena. 2010. Curricularización de la extensión: ¿por qué, cuál, cómo? Integralidad: tensiones y perspectivas, 9. find
  3. Gonzalo Berger, Tatiana Rischewski, Luis Chiruzzo, and Aiala Rosá. 2022. Generation of english question answer exercises from texts using transformers based models. In 2022 IEEE Latin American Conference on Computational Intelligence (LA-CCI). IEEE. find
  4. Claudia Brovetto. 2015. Ceibal en Inglés. Un caso de integración de pedagogía y tecnología. In Octavo Foro de Lenguas de ANEP, pages 13–22. Programa de Políticas lingüísticas, Montevideo, Uruguay. find
  5. J. Burstein, J. Sabatini, J. Shore, B. Moulder, and J. Lentini. 2013. A user study: Technology to increase teachers’ linguistic awareness to improve instructional language support for english language learners. In Proceedings of the 2nd Workshop on Natural Language Processing for Improving Textual Accessibility (NLP4ITA), Atlanta, Georgia. Association for Computational Linguistics.
  6. Jennifer Esteche, Romina Romero, Luis Chiruzzo, and Aiala Rosa. 2017. Automatic definition extraction and crossword generation from spanish news text. CLEI Electronic Journal, 20(2). ↗
  7. Alena Fenogenova and Elizaveta Kuzmenko. 2016. Automatic generation of lexical exercises. In Proceedings of the Workshop on Computational Linguistics and Language Science. find
  8. Bernabé González, Isabel Ivagnes, Joaquín Lejtreger, Luis Chiruzzo, and Aiala Rosá. 2021. Application of language technologies to assist english teaching. In 2021 40th International Conference of the Chilean Computer Science Society (SCCC), pages 1–8. IEEE. find
  9. Anisia Katinskaia, Javad Nouri, and Roman Yangarber. 2018. Revita: a language-learning platform at the intersection of its and call. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japón. European Language Resources Association (ELRA). find
  10. Diane Litman. 2016. Natural language processing for enhancing teaching and learning. In Thirtieth AAAI conference on artificial intelligence. find
  11. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. ↗
  12. Martín Morón, Joaquín Scocozza, Luis Chiruzzo, and Aiala Rosá. 2021. A tool for automatic question generation for teaching english to beginner students. In 2021 40th International Conference of the Chilean Computer Science Society (SCCC), pages 1–5. IEEE. find
  13. Analía Percovich, Alejandro Tosi, Luis Chiruzzo, and Aiala Rosá. 2019. Ludic applications for language teaching support using natural language processing. In 2019 38th International Conference of the Chilean Computer Science Society (SCCC), pages 1–7. IEEE. find
  14. 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. Journal of Machine Learning Research, 21(140):1–67. ↗
  15. Shirley Romano. 2019. Inglés sin Límites: Un proyecto democrático de enseñanza de inglés en Educación Primaria Rural. pages 9–17. ANEP. find
  16. Limber Santos. 2016. La Didáctica Multigrado más allá de la escuela rural. Quehacer Educativo, 140:91–99. find
  17. Elena Volodina, Lars Borin, and Ildikó Pilán, editors. 2014. Proceedings of the third workshop on NLP for computer-assisted language learning. LiU Electronic Press, Uppsala, Sweden. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chiruzzo-2022-nlp-support-english-teaching-rural/