Automated Run-On Sentence Detection and Correction for Educational Writing
Saved in:
| Title: | Automated Run-On Sentence Detection and Correction for Educational Writing |
|---|---|
| Language: | English |
| Authors: | Shubham Chakraborty, Yu Tian, Michelle Banawan, Andrew Potter (ORCID |
| Source: | Grantee Submission. 2026. |
| Peer Reviewed: | Y |
| Page Count: | 5 |
| Publication Date: | 2026 |
| Sponsoring Agency: | National Center for Education Research (NCER) (ED/IES) |
| Contract Number: | R305T240035 R305N210041 |
| Document Type: | Speeches/Meeting Papers Reports - Research |
| Descriptors: | Writing Evaluation, Natural Language Processing, Artificial Intelligence, Sentence Structure, Grammar, Error Correction, Automation, Student Writing Models, Instructional Design |
| Abstract: | Run-on sentences, including fused sentences, comma splices, and conjunctive adverb misuse, pose a persistent challenge in student writing, undermining both human evaluation and automated analyses in learning environments. Despite their instructional importance, run-ons are underrepresented in major grammatical error correction (GEC) benchmarks. We present a two-stage NLP pipeline for run-on detection and minimal-change correction, designed within the Learning Engineering Framework to improve writing feedback while preserving student voice. Early annotation of 251 student sentences identified 29 potential run-ons, informing our pipeline design and human validation workflows. [This paper was published in: "Proceedings of the Learning Engineering Research Network Convening (LERN 2026)," 2026, pp. 160-163.] |
| Abstractor: | As Provided |
| IES Funded: | Yes |
| Entry Date: | 2026 |
| Access URL: | https://edtecharchives.org/conference_proceeding/2551/25361 |
| Accession Number: | ED678820 |
| Database: | ERIC |
| Abstract: | Run-on sentences, including fused sentences, comma splices, and conjunctive adverb misuse, pose a persistent challenge in student writing, undermining both human evaluation and automated analyses in learning environments. Despite their instructional importance, run-ons are underrepresented in major grammatical error correction (GEC) benchmarks. We present a two-stage NLP pipeline for run-on detection and minimal-change correction, designed within the Learning Engineering Framework to improve writing feedback while preserving student voice. Early annotation of 251 student sentences identified 29 potential run-ons, informing our pipeline design and human validation workflows. [This paper was published in: "Proceedings of the Learning Engineering Research Network Convening (LERN 2026)," 2026, pp. 160-163.] |
|---|
