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

Sentence 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. Disciplines Computer Sciences Comments Nenkova, 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: 10.1007/ 978-3-642-15573-4_12 This conference paper is available at ScholarlyCommons: http://repository.upenn.edu/cis_papers/715 Structural Features for Predicting the Linguistic Quality of Text Applications to Machine Translation, Automatic Summarization and Human-Authored Text Ani Nenkova, Jieun Chae, Annie Louis, and Emily Pitler University of Pennsylvania {nenkova,chaeji,lannie,epitler}@seas.upenn.edu Abstract. Sentence 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 Sentence 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.