{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:34:17Z","timestamp":1768095257698,"version":"3.49.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T00:00:00Z","timestamp":1694995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>In this study, we focus on sentence splitting, a subfield of text simplification, motivated largely by an unproven idea that if you divide a sentence in pieces, it should become easier to understand. Our primary goal in this study is to find out whether this is true. In particular, we ask, does it matter whether we break a sentence into two, three, or more? We report on our findings based on Amazon Mechanical Turk. More specifically, we introduce a Bayesian modeling framework to further investigate to what degree a particular way of splitting the complex sentence affects readability, along with a number of other parameters adopted from diverse perspectives, including clinical linguistics, and cognitive linguistics. The Bayesian modeling experiment provides clear evidence that bisecting the sentence leads to enhanced readability to a degree greater than when we create simplification with more splits.<\/jats:p>","DOI":"10.3389\/frai.2023.1208451","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T07:34:11Z","timestamp":1695108851000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Does splitting make sentence easier?"],"prefix":"10.3389","volume":"6","author":[{"given":"Tadashi","family":"Nomoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.3758\/s13428-017-0926-2","article-title":"Conversation level syntax similarity metric","volume":"50","author":"Boghrati","year":"2018","journal-title":"Beha. Res. Methods"},{"key":"B2","doi-asserted-by":"crossref","first-page":"732","DOI":"10.18653\/v1\/D18-1080","article-title":"\u201cLearning to split and rephrase from Wikipedia edit history,\u201d","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Botha","year":"2018"},{"key":"B3","volume-title":"Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach","author":"Burnham","year":"2003"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v103.i15","article-title":"Bambi: a simple interface for fitting Bayesian linear models in python","author":"Capretto","year":"2020","journal-title":"J. Stat. Softw."},{"key":"B5","author":"Chall","year":"1995","journal-title":"Readability Revisited: The New Dale-Chall Readability Formula"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.08299","article-title":"Fastkassim: a fast tree kernel-based syntactic similarity metric","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv:2203.08299"},{"key":"B7","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1214\/09-AOAS285","article-title":"BART: Bayesian additive regression trees","volume":"4","author":"Chipman","year":"2010","journal-title":"Ann. Appl. Stat"},{"key":"B8","first-page":"263","article-title":"\u201cNew ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron,\u201d","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Collins","year":"2002"},{"key":"B9","first-page":"84","article-title":"Text readability and intuitive simplification: a comparison of readability formulas","volume":"23","author":"Crossley","year":"2011","journal-title":"Read. For. Lang"},{"key":"B10","first-page":"92","article-title":"What's so simple about simplified texts? A computational and psycholinguistic investigation for text comprehension and text processing","volume":"26","author":"Crossley","year":"2014","journal-title":"Read. For. Lang"},{"key":"B11","volume-title":"The Art of Readable Writing","author":"Flesch","year":"1949"},{"key":"B12","volume-title":"How to Write Plain English: A Book for Lawyers and Consumers","author":"Flesch","year":"1979"},{"key":"B13","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1017\/CBO9780511597855.005","article-title":"\u201cSyntactic complexity,\u201d","volume-title":"Natural Language Parsing: Psychological, Computational, and Theoretical Perspectives, Studies in Natural Language Processing","author":"Frazier","year":"1985"},{"key":"B14","author":"Frost","year":"2019"},{"key":"B15","doi-asserted-by":"crossref","first-page":"179","DOI":"10.18653\/v1\/P17-1017","article-title":"\u201cCreating training corpora for NLG micro-planners,\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Gardent","year":"2017"},{"key":"B16","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1214\/ss\/1177011136","article-title":"Inference from iterative simulation using multiple sequences","volume":"7","author":"Gelman","year":"1992","journal-title":"Stat. Sci"},{"key":"B17","doi-asserted-by":"crossref","first-page":"6193","DOI":"10.18653\/v1\/2021.emnlp-main.500","article-title":"\u201cBiSECT: learning to split and rephrase sentences with bitexts,\u201d","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Kim","year":"2021"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.21236\/ADA006655","author":"Kincaid","year":"1975","journal-title":"Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel"},{"key":"B19","volume-title":"A Student's Guide to Bayesian Statistics","author":"Lambert","year":"2018"},{"key":"B20","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.18653\/v1\/D15-1148","article-title":"\u201cDetecting content-heavy sentences: a cross-language case study,\u201d","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Li","year":"2015"},{"key":"B21","doi-asserted-by":"publisher","first-page":"543","DOI":"10.29220\/CSAM.2017.24.6.543","article-title":"A review of tree-based Bayesian methods","volume":"24","author":"Linero","year":"2017","journal-title":"Commun. Stat. Appl. Methods"},{"key":"B22","doi-asserted-by":"crossref","first-page":"276","DOI":"10.3115\/981658.981695","article-title":"\u201cStatistical decision-tree models for parsing,\u201d","volume-title":"33rd Annual Meeting of the Association for Computational Linguistics","author":"Magerman","year":"1995"},{"key":"B23","author":"Mason","year":"1978","journal-title":"Facilitating Reading Comprehension Through Text Structure Manipulation"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511894664","volume-title":"Automated Evaluation of Text and Discourse With Coh-Metrix","author":"McNamara","year":"2014"},{"key":"B25","first-page":"113","article-title":"\u201cMaking tree kernels practical for natural language learning,\u201d","volume-title":"11th Conference of the European Chapter of the Association for Computational Linguistics","author":"Moschitti","year":"2006"},{"key":"B26","first-page":"606","article-title":"\u201cSplit and rephrase,\u201d","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Narayan","year":"2017"},{"key":"B27","doi-asserted-by":"crossref","first-page":"118","DOI":"10.18653\/v1\/W19-8615","article-title":"\u201cMinWikiSplit: a sentence splitting corpus with minimal propositions,\u201d","volume-title":"Proceedings of the 12th International Conference on Natural Language Generation","author":"Niklaus","year":"2019"},{"key":"B28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18653\/v1\/2022.tsar-1.1","article-title":"\u201cThe fewer splits are better: deconstructing readability in sentence splitting,\u201d","volume-title":"Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)","author":"Nomoto","year":"2022"},{"key":"B29","doi-asserted-by":"publisher","first-page":"598833","DOI":"10.3389\/fams.2021.598833","article-title":"An explainable Bayesian decision tree algorithm","volume":"7","author":"Nuti","year":"2021","journal-title":"Front. Appl. Math. Stat"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1145\/2461121.2461126","article-title":"\u201cSimplify or help? Text simplification strategies for people with dyslexia,\u201d","volume-title":"Proceedings of the 10th International Cross-Disciplinary Conference on Web Accessibility, W4A '13","author":"Rello","year":"2013"},{"key":"B31","first-page":"1","article-title":"\u201cSyntactic complexity measures for detecting mild cognitive impairment,\u201d","volume-title":"Biological, Translational, and Clinical Language Processing","author":"Roark","year":"2007"},{"key":"B32","first-page":"1","article-title":"Simplification or elaboration? The effects of two types of text modifications on foreign language reading comprehension","volume":"10","author":"Ross","year":"1991","journal-title":"Univ. Hawai'i Work. Pap. ESL"},{"key":"B33","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1111\/1467-9868.00353","article-title":"Bayesian measures of model complexity and fit","volume":"64","author":"Spiegelhalter","year":"2002","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"B34","first-page":"230","article-title":"\u201cCan text simplification help machine translation?,\u201d","volume-title":"Proceedings of the 19th Annual Conference of the European Association for Machine Translation","author":"\u0160tajner","year":"2016"},{"key":"B35","doi-asserted-by":"crossref","first-page":"39","DOI":"10.18653\/v1\/W18-7006","article-title":"\u201cImproving machine translation of English relative clauses with automatic text simplification,\u201d","volume-title":"Proceedings of the 1st Workshop on Automatic Text Adaptation (ATA)","author":"\u0160tajner","year":"2018"},{"key":"B36","first-page":"738","article-title":"\u201cBLEU is not suitable for the evaluation of text simplification,\u201d","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Sulem","year":""},{"key":"B37","first-page":"685","article-title":"\u201cSemantic structural evaluation for text simplification,\u201d","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Sulem","year":""},{"key":"B38","first-page":"50","article-title":"\u201cSemantic structural decomposition for neural machine translation,\u201d","volume-title":"Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics","author":"Sulem","year":"2020"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1007\/s11222-016-9696-4","article-title":"Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC","volume":"27","author":"Vehtari","year":"2016","journal-title":"Stat. Comput"},{"key":"B40","doi-asserted-by":"publisher","first-page":"19","DOI":"10.5121\/mlaij.2016.3103","article-title":"A survey on similarity measures in text mining","volume":"3","author":"Vijaymeena","year":"2016","journal-title":"Mach. Learn. Appl"},{"key":"B41","first-page":"3571","article-title":"Asymptotic equivalence of bayes cross validation and widely applicable information criterion in singular learning theory","author":"Watanabe","year":"2010","journal-title":"J. Mach. Learn. Res"},{"key":"B42","article-title":"\u201cExperiments with discourse-level choices and readability,\u201d","volume-title":"Proceedings of the 9th European Workshop on Natural Language Generation (ENLG-2003) at EACL 2003","author":"Williams","year":"2003"},{"key":"B43","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1162\/tacl_a_00139","article-title":"Problems in current text simplification research: new data can help","volume":"3","author":"Xu","year":"2015","journal-title":"Trans. Assoc. Comput. Linguist"},{"key":"B44","first-page":"444","article-title":"A model and an hypothesis for language structure","volume":"104","author":"Yngve","year":"1960","journal-title":"Proc. Am. Philos. Soc"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1137\/0218082","article-title":"Simple fast algorithms for the editing distance between trees and related problems","volume":"18","author":"Zhang","year":"1989","journal-title":"SIAM J. Comput"},{"key":"B46","first-page":"584","article-title":"\u201cSentence simplification with deep reinforcement learning,\u201d","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Zhang","year":"2017"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1208451\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T07:34:34Z","timestamp":1695108874000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1208451\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,18]]},"references-count":46,"alternative-id":["10.3389\/frai.2023.1208451"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1208451","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,18]]},"article-number":"1208451"}}