Proceedings of the 2018 EMNLP Workshop W-Nut: The 4th Workshop on Noisy User-Generated Text 2018
DOI: 10.18653/v1/w18-6105
|View full text |Cite
|
Sign up to set email alerts
|

How do you correct run-on sentences it’s not as easy as it seems

Abstract: Run-on sentences are common grammatical mistakes but little research has tackled this problem to date. This work introduces two machine learning models to correct run-on sentences that outperform leading methods for related tasks, punctuation restoration and wholesentence grammatical error correction. Due to the limited annotated data for this error, we experiment with artificially generating training data from clean newswire text. Our findings suggest artificial training data is viable for this task. We discu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 13 publications
0
3
0
Order By: Relevance
“…Run-on sentences: consist of at least two main or independent clauses that are not combined by a conjunction or divided by a punctuation mark (Zheng et al, 2018).…”
Section: Research Question 2: How Many Types Of Sentence Structures D...mentioning
confidence: 99%
“…Run-on sentences: consist of at least two main or independent clauses that are not combined by a conjunction or divided by a punctuation mark (Zheng et al, 2018).…”
Section: Research Question 2: How Many Types Of Sentence Structures D...mentioning
confidence: 99%
“…Error types are often used to improve performance and evaluation in GEC. Taxonomies have been used to construct classifiers and rule-based engines to correct specific error types (e.g., Zheng et al, 2018). When using end-to-end systems, balancing the distribution of errors in the train and test sets has been shown to improve results (Junczys-Dowmunt et al, 2018).…”
Section: Related Workmentioning
confidence: 99%
“…For spell checking, Flor and Futagi (2012) used document-level context to check if a candidate correction for a misspelled word had been used earlier in the document. Zheng et al (2018) proposed splitting runon sentences into separate sentences. However, they did not use cross-sentence context.…”
Section: Related Workmentioning
confidence: 99%