TY - GEN
T1 - The effect of different writing tasks on linguistic style
T2 - 21st Conference on Computational Natural Language Learning, CoNLL 2017
AU - Schwartz, Roy
AU - Sap, Maarten
AU - Konstas, Ioannis
AU - Zilles, Li
AU - Choi, Yejin
AU - Smith, Noah A.
N1 - Funding Information: The authors thank Chenhao Tan, Luke Zettle-moyer, Rik Koncel-Kedziorski, Rowan Zellers, Yangfeng Ji and several anonymous reviewers for helpful feedback. This research was supported in part by Darpa CwC program through ARO (W911NF-15-1-0543), Samsung GRO, NSF IIS-1524371, and gifts from Google and Facebook. Funding Information: The authors thank Chenhao Tan, Luke Zettlemoyer, Rik Koncel-Kedziorski, Rowan Zellers, Yangfeng Ji and several anonymous reviewers for helpful feedback. This research was supported in part by Darpa CwC program through ARO (W911NF-15-1-0543), Samsung GRO, NSF IIS-1524371, and gifts from Google and Facebook. Publisher Copyright: © 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - A writer’s style depends not just on personal traits but also on her intent and mental state. In this paper, we show how variants of the same writing task can lead to measurable differences in writing style. We present a case study based on the story cloze task (Mostafazadeh et al., 2016a), where annotators were assigned similar writing tasks with different constraints: (1) writing an entire story, (2) adding a story ending for a given story context, and (3) adding an incoherent ending to a story. We show that a simple linear classifier informed by stylistic features is able to successfully distinguish among the three cases, without even looking at the story context. In addition, combining our stylistic features with language model predictions reaches state of the art performance on the story cloze challenge. Our results demonstrate that different task framings can dramatically affect the way people write.1
AB - A writer’s style depends not just on personal traits but also on her intent and mental state. In this paper, we show how variants of the same writing task can lead to measurable differences in writing style. We present a case study based on the story cloze task (Mostafazadeh et al., 2016a), where annotators were assigned similar writing tasks with different constraints: (1) writing an entire story, (2) adding a story ending for a given story context, and (3) adding an incoherent ending to a story. We show that a simple linear classifier informed by stylistic features is able to successfully distinguish among the three cases, without even looking at the story context. In addition, combining our stylistic features with language model predictions reaches state of the art performance on the story cloze challenge. Our results demonstrate that different task framings can dramatically affect the way people write.1
UR - http://www.scopus.com/inward/record.url?scp=85063089960&partnerID=8YFLogxK
U2 - https://doi.org/10.18653/v1/k17-1004
DO - https://doi.org/10.18653/v1/k17-1004
M3 - Conference contribution
T3 - CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings
SP - 15
EP - 25
BT - CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings
PB - Association for Computational Linguistics (ACL)
Y2 - 3 August 2017 through 4 August 2017
ER -