Elamur Research⌕
☰
home / papers / 2026 / TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech

TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech

Paper · 2026 · Shamira Venturini, Oliver Hennhöfer, Steffen Kinkel et al.

Summary

Coding morphosyntactic errors in spoken-language transcripts helps researchers study grammatical development and disorders such as DLD, Down syndrome and autism. Doing it by hand is slow and requires experts, and no TalkBank tool (MOR, GRASP, CLAN) currently assigns error codes automatically. The authors present TalkTag, which treats CHAT word-level error coding as constrained structured generation. Given an utterance, the model inserts inline tags and, where possible, reconstructs the intended target form. Annotated child-language data is very scarce, so they used LoRA to fine-tune a small open-weight instruction-tuned LLM on children's narrative transcripts, adding synthetic data to cover rare error patterns. To assess the system, they combined automated metrics, a blinded adjudication carried out after the fact, and manual inspection of ENNI material the model had not encountered before. The resulting tags were reasonably precise, silent misses were rare, and many remaining difficulties came from genuinely ambiguous cases. The authors therefore position TalkTag as a human-in-the-loop pre-annotation aid rather than a replacement for expert annotators. It offers a scalable first-pass option for clinical and developmental research.

Key points

  • Label scope: TalkTag covers a subset of CHAT error codes:
    • morphological [* m:*] codes, such as missing, over-regularised, superfluous or double-marked morphemes;
    • same-category substitutions [* s:r:*];
    • wrong-grammatical-category substitutions [* s:r:gc:*].
  • Target reconstruction: Targets are written as [: target] for non-word errors and [:: target] for real-word errors. The Python package post-processes output to match the newer CHAT [= target] convention.
  • Data and evaluation: All real-data evaluation used the ENNI corpus (CHILDES). Transfer to other corpora, age groups, clinical populations, L2 learners or adult speech has not been tested.
  • Known gaps: The model does not annotate missing parts of speech (e.g., omitted auxiliaries). Rare error types also remain weakly supported.
  • Code release: The tool is available on GitHub (OliverHennhoefer/talk-tag). The training data is not redistributed and must be obtained from TalkBank/CHILDES under its licence.

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

🎓Karlsruhe Institute of TechnologyKarlsruhe · Germany12 works · 834 citations🎓Karlsruhe University of Applied SciencesKarlsruhe · Germany4 works · 47 citations

 Fields, topics and concepts

📚 Shelves 6The 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 worksPsychology · 1,552 worksDevelopmental and Educational Psychology · 499 works

Cite

Cite as Shamira Venturini, Oliver Hennhöfer, Steffen Kinkel and Jannik Strötgen. 2026. TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech. Proceedings of the 20th Linguistic Annotation Workshop (LAW XX).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.law-main.20

@inproceedings{venturini2026talktag,
  title = {{TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech}},
  author = {Shamira Venturini, Oliver Hennhöfer, Steffen Kinkel and Jannik Strötgen},
  booktitle = {Proceedings of the 20th Linguistic Annotation Workshop (LAW XX)},
  year = {2026},
  doi = {10.18653/v1/2026.law-main.20},
  url = {https://doi.org/10.18653/v1/2026.law-main.20}
}

References

48 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abeer Z. Al-Marridi, Samawiyah M. Ulde, Ahmed Bensaid, and Tariq A. Khwaileh. 2026. Speech and language disorders: A systematic review of corpora and future directions. Applied Corpus Linguistics, 6(1):100186. find
  2. Erika Benassi, Sonia Boria, Maria Teresa Berghenti, Michela Camia, Maristella Scorza, and Giuseppe Cossu. 2021. Morpho-syntactic deficit in children with cochlear implant: Consequence of hearing loss or concomitant impairment to the language system? International Journal of Environmental Research an… find
  3. Samane Dehghani Golestani, Nahid Jalilevand, and Mohammad Kamali. 2018. A comparison of morphosyntactic abilities in deaf children with cochlear implant and 5-year-old normal-hearing children. International Journal of Pediatric Otorhinolaryngology, 110:27–30. find
  4. Christopher Bryant, Mariano Felice, Øistein E. Andersen, and Ted Briscoe. 2019. The BEA-2019 shared task on grammatical error correction. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 52–75, Florence, Italy. Association for Computatio…
  5. Christopher Bryant, Zheng Yuan, Muhammad Reza Qorib, Hannan Cao, Hwee Tou Ng, and Ted Briscoe. 2023. Grammatical error correction: A survey of the state of the art. Computational Linguistics, pages 1–59. find
  6. Louise Cummings. 2023. Communication disorders: A complex population in healthcare. Language and Health, 1(2):12–19. find
  7. Daniel Dahlmeier, Hwee Tou Ng, and Siew Mei Wu. 2013. Building a large annotated corpus of learner English: The NUS corpus of learner English. In Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications, pages 22–31, Atlanta, Georgia. Association for Computat…
  8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  9. P. A. Eadie, M. E. Fey, J. M. Douglas, and C. L. Parsons. 2002. Profiles of grammatical morphology and sentence imitation in children with specific language impairment and down syndrome. Journal of Speech, Language, and Hearing Research, 45(4):720–732. find
  10. Karën Fort and Benoît Sagot. 2010. Influence of pre-annotation on POS-tagged corpus development. In Proceedings of the Fourth Linguistic Annotation Workshop, pages 56–63, Uppsala, Sweden. Association for Computational Linguistics. find
  11. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  12. Khairun-nisa Hassanali and Yang Liu. 2011. Measuring language development in early childhood education: A case study of grammar checking in child language transcripts. In Proceedings of the Sixth Workshop on Innovative Use of NLP for Building Educational Applications, pages 87–95, Portland, Oregon.…
  13. Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, and Dietrich Klakow. 2021. A survey on recent approaches for natural language processing in low-resource scenarios. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Hu…
  14. Timothy Huang and Lizbeth Finestack. 2020. Comparing morphosyntactic profiles of children with developmental language disorder or language disorder associated with autism spectrum disorder. American Journal of Speech-Language Pathology, 29(2):714– 731. find
  15. Dimitra Katsarou and Georgia Andreou. 2022. Morphosyntactic abilities in young children with down syndrome: Evidence from the greek language. International Journal of Language & Communication Disorders, 57(5):937–947. find
  16. Katerina Korre and John Pavlopoulos. 2020. ERRANT: Assessing and improving grammatical error type classification. In Proceedings of the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 85–89, Online. International Committ… find
  17. Gloria Gagliardi and Marta Maffia. 2024. Language resources for clinical linguistics: introduction to the special issue. Language Resources and Evaluation, 58(3):859–863. find
  18. Laurence B. Leonard and Patricia Deevy. 2020. Retrieval practice and word learning in children with specific language impairment and their typically developing peers. Journal of Speech, Language, and Hearing Research, 63(10):3252–3262. find
  19. Christopher Gebauer, Lars Rumberg, Lars Köhn, Hanna Ehlert, Edith Beaulac, and Jörn Ostermann. 2025. Grammatical Error Detection on Spontaneous Children’s Speech Using Iterative Pseudo Labeling. In Interspeech 2025, pages 2865–2869. find
  20. Todd Lingren, Louise Deleger, Katalin Molnar, Haijun Zhai, Jareen Meinzen-Derr, Megan Kaiser, Laura Stoutenborough, Qi Li, and Imre Solti. 2014. Evaluating the impact of pre-annotation on annotation speed and potential bias: natural language processing gold standard development for clinical named en… find
  21. Eric Morley, Brian Roark, and Jan P. H. Santen. 2013. The utility of manual and automatic linguistic error codes for identifying neurodevelopmental disorders. In BEA@NAACL-HLT. find
  22. Brian MacWhinney. 2000. The CHILDES project: The database, volume 2. Psychology Press. find
  23. Courtney Napoles, Keisuke Sakaguchi, and Joel Tetreault. 2017. JFLEG: A fluency corpus and benchmark for grammatical error correction. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 229–234, Valencia, Spai… find
  24. Brian MacWhinney. 2012. Morphosyntactic analysis of the CHILDES and TalkBank corpora. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2375–2380, Istanbul, Turkey. European Language Resources Association (ELRA).
  25. Brian MacWhinney. 2019. Chat manual. find
  26. Brian MacWhinney, Steven Bird, Christopher Cieri, and Craig Martell. 2004. Talkbank: Building an open unified multimodal database of communicative interaction. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Re… find
  27. Brian MacWhinney and Davida Fromm. 2022. Language sample analysis with talkbank: An update and review. Frontiers in Communication, 7. find
  28. Gary F. Marcus, Steven Pinker, Michael Ullman, Michelle Hollander, T. John Rosen, and Fei Xu. 1992. Overregularization in language acquisition. Monographs of the Society for Research in Child Development, 57(4):1–182. find
  29. Marie Mikulová, Milan Straka, Jan Štěpánek, Barbora Štěpánková, and Jan Hajic. 2022. Quality and efficiency of manual annotation: Pre-annotation bias. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2909–2918, Marseille, France. European Language Resources Asso… find
  30. Jon F. Miller, Karen Andriacchi, and Ann Nockerts. 2011. Assessing Language Production Using SALT Software: A Clinician’s Guide to Language Sample Analysis. SALT Software, LLC. find
  31. Tomoya Mizumoto, Yuta Hayashibe, Mamoru Komachi, Masaaki Nagata, and Yuji Matsumoto. 2012. The effect of learner corpus size in grammatical error correction of ESL writings. In Proceedings of COLING 2012: Posters, pages 863–872, Mumbai, India. find
  32. The COLING 2012 Organizing Committee. find
  33. Esther Moraleda-Sepúlveda and Patricia López-Resa. 2022. Morphological difficulties in people with developmental language disorder. Children, 9(2):125. find
  34. Eric Morley, Anna Eva Hallin, and Brian Roark. 2014. Data driven grammatical error detection in transcripts of children’s speech. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 980–989, Doha, Qatar. Association for Computational Linguistics. find
  35. Hwee Tou Ng, Siew Mei Wu, Ted Briscoe, Christian Hadiwinoto, Raymond Hendy Susanto, and Christopher Bryant. 2014. The CoNLL-2014 shared task on grammatical error correction. In Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task, pages 1–14, Baltimore, Ma… find
  36. Hwee Tou Ng, Siew Mei Wu, Yuanbin Wu, Christian Hadiwinoto, and Joel Tetreault. 2013. The CoNLL-2013 shared task on grammatical error correction. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning: Shared Task, pages 1–12, Sofia, Bulgaria. Association for Computa… find
  37. Mitja Nikolaus, Abhishek Agrawal, Petros Kaklamanis, Alex Warstadt, and Abdellah Fourtassi. 2024. Automatic annotation of grammaticality in child-caregiver conversations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-C…
  38. Jack L. Paradise, Thomas F. Campbell, Christine A. Dollaghan, Heidi M. Feldman, Beverly S. Bernard, D. Kathleen Colborn, Howard E. Rockette, Janine E. Janosky, Dayna L. Pitcairn, Marcia Kurs-Lasky, Diane L. Sabo, and Clyde G. Smith. 2005. Developmental outcomes after early or delayed insertion of ty… find
  39. Martina Penke. 2019. Regular and irregular inflection in down syndrome – new evidence from german. Cortex, 116:192–208. find
  40. Mabel L. Rice and Kenneth Wexler. 1996. Toward tense as a clinical marker of specific language impairment in english-speaking children. Journal of Speech and Hearing Research, 39(6):1239–1257. find
  41. Mabel L. Rice, Kenneth Wexler, and Scott Hershberger. 1998. Tense over time: The longitudinal course of tense acquisition in children with specific language impairment. Journal of Speech, Language, and Hearing Research, 41(6):1412–1431. find
  42. Lars Rumberg, Christopher Gebauer, Hanna Ehlert, Maren Wallbaum, Lena Bornholt, Jörn Ostermann, and Ulrike Lüdtke. 2022. kidstalc: A corpus of 3- to 11-year-old german children’s connected natural speech. In Interspeech 2022, interspeech_2022, pages 5160–5164. ISCA. find
  43. Kenji Sagae, Alon Lavie, and Brian MacWhinney. 2005. Automatic measurement of syntactic development in child language. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 197–204, Ann Arbor, Michigan. Association for Computational Linguistics. find
  44. Phyllis Schneider, Denyse Hayward, and Rita Vis Dubé. 2006. Edmonton narrative norms instrument. find
  45. Toshikazu Tajiri, Mamoru Komachi, and Yuji Matsumoto. 2012. Tense and aspect error correction for ESL learners using global context. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 198–202, Jeju Island, Korea. Association for…
  46. Kenneth Wexler, Carson T. Schütze, and Mabel Rice. 1998. Subject case in children with SLI and unaffected controls: Evidence for the Agr/Tns omission model. Language Acquisition, 7(2–4):317–344. find
  47. Bernadette Witecy, Eva Wimmer, Isabel Neitzel, and Martina Penke. 2023. Morphosyntactic development in german-speaking individuals with down syndrome– longitudinal data. Frontiers in Psychology, 14. find
  48. Helen Yannakoudakis, Ted Briscoe, and Ben Medlock. 2011. A new dataset and method for automatically grading ESOL texts. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 180–189, Portland, Oregon, USA. Association for Compu…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/venturini-2026-talktag-fine-grained-morphosyntactic-error/