Structural Features for Predicting the Linguistic Quality of Text: Applications to Machine Translation, Automatic Summarization and Human-Authored Text

Simple item page
dc.contributor.authorNenkova, Ani
dc.contributor.authorChae, Jieun
dc.contributor.authorLouis, Annie
dc.contributor.authorPitler, Emily
dc.date2023-05-17T07:16:54.000
dc.date.accessioned2023-05-22T12:50:36Z
dc.date.available2023-05-22T12:50:36Z
dc.date.issued2010-01-01
dc.date.submitted2012-07-30T12:09:55-07:00
dc.description.abstractSentence structure is considered to be an important component of the overall linguistic quality of text. Yet few empirical studies have sought to characterize how and to what extent structural features determine fluency and linguistic quality. We report the results of experiments on the predictive power of syntactic phrasing statistics and other structural features for these aspects of text. Manual assessments of sentence fluency for machine translation evaluation and text quality for summarization evaluation are used as gold-standard. We find that many structural features related to phrase length are weakly but significantly correlated with fluency and classifiers based on the entire suite of structural features can achieve high accuracy in pairwise comparison of sentence fluency and in distinguishing machine translations from human translations. We also test the hypothesis that the learned models capture general fluency properties applicable to human-authored text. The results from our experiments do not support the hypothesis. At the same time structural features and models based on them prove to be robust for automatic evaluation of the linguistic quality of multi-document summaries.
dc.description.commentsNenkova, A., Chae, J., Louis, A., & Pitler, E., Structural Features for Predicting the Linguistic Quality of Text: Applications to Machine Translation, Automatic Summarization and Human-Authored Text, Empirical Methods in Natural Language Generation: Data Oriented Methods and Empirical Evaluation, 2010, doi: http://dx.doi.org/10.1007/978-3-642-15573-4_12
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/6782
dc.legacy.articleid1755
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1755&context=cis_papers&unstamped=1
dc.source.issue715
dc.source.journalDepartmental Papers (CIS)
dc.source.statuspublished
dc.subject.otherComputer Sciences
dc.titleStructural Features for Predicting the Linguistic Quality of Text: Applications to Machine Translation, Automatic Summarization and Human-Authored Text
dc.typePresentation
digcom.identifiercis_papers/715
digcom.identifier.contextkey3160101
digcom.identifier.submissionpathcis_papers/715
digcom.typeconference
dspace.entity.typePublication
relation.isAuthorOfPublicationce994fec-4416-487d-9b37-34b89c8f432b
relation.isAuthorOfPublication.latestForDiscoveryce994fec-4416-487d-9b37-34b89c8f432b
upenn.schoolDepartmentCenterDepartmental Papers (CIS)
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2010_structural_features_for_predicting_the_linguistic_quality_of_text__applications_to_machine_translation__automatic_summarization_and_human_authored_text.pdf
Size:
250.35 KB
Format:
Adobe Portable Document Format
Download
Collection
Presentations