Supporting ESL Writing by Prompting Crowdsourced Structural Feedback.

Yi-Ching Huang; Jiunn-Chia Huang; Hao-Chuan Wang; Jane Yung-jen Hsu

Supporting ESL Writing by Prompting Crowdsourced Structural Feedback.

Yi-Ching Huang, Jiunn-Chia Huang, Hao-Chuan Wang, Jane Yung-jen Hsu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

5 Citations (Scopus)

20 Downloads (Pure)

Abstract

Writing is challenging, especially for non-native speakers. To support English as a Second Language (ESL) writing, we propose StructFeed, which allows native speakers to annotate topic sentence and relevant keywords in texts and generate writing hints based on the principle of paragraph unity. First, we compared our crowd-based method with three na¨ıve machine learning (ML) methods and got the best performance on the identiﬁcation of topic sentence and irrelevant sentence in the article. Next, we evaluated the StructFeed system with two feedback-generation mechanisms including feedback generated by one expert and by one crowd worker. The results showed that people who received feedback by StructFeed got the highest improvement after revision.

Original language	English
Title of host publication	Proceedings of the AAAI Conference on Human Computation and Crowdsourcing
Pages	71-78
Publication status	Published - 2017
Externally published	Yes

Access to Document

Huang2017-hcompFinal author version , 2.97 MB

Cite this

@inproceedings{b016f69b0f9f46da8a9ee23187c78b5c,

title = "Supporting ESL Writing by Prompting Crowdsourced Structural Feedback.",

abstract = "Writing is challenging, especially for non-native speakers. To support English as a Second Language (ESL) writing, we propose StructFeed, which allows native speakers to annotate topic sentence and relevant keywords in texts and generate writing hints based on the principle of paragraph unity. First, we compared our crowd-based method with three na¨ıve machine learning (ML) methods and got the best performance on the identiﬁcation of topic sentence and irrelevant sentence in the article. Next, we evaluated the StructFeed system with two feedback-generation mechanisms including feedback generated by one expert and by one crowd worker. The results showed that people who received feedback by StructFeed got the highest improvement after revision.",

author = "Yi-Ching Huang and Jiunn-Chia Huang and Hao-Chuan Wang and Hsu, \{Jane Yung-jen\}",

year = "2017",

language = "English",

pages = "71--78",

booktitle = "Proceedings of the AAAI Conference on Human Computation and Crowdsourcing",

}

TY - GEN

T1 - Supporting ESL Writing by Prompting Crowdsourced Structural Feedback.

AU - Huang, Yi-Ching

AU - Huang, Jiunn-Chia

AU - Wang, Hao-Chuan

AU - Hsu, Jane Yung-jen

PY - 2017

Y1 - 2017

N2 - Writing is challenging, especially for non-native speakers. To support English as a Second Language (ESL) writing, we propose StructFeed, which allows native speakers to annotate topic sentence and relevant keywords in texts and generate writing hints based on the principle of paragraph unity. First, we compared our crowd-based method with three na¨ıve machine learning (ML) methods and got the best performance on the identiﬁcation of topic sentence and irrelevant sentence in the article. Next, we evaluated the StructFeed system with two feedback-generation mechanisms including feedback generated by one expert and by one crowd worker. The results showed that people who received feedback by StructFeed got the highest improvement after revision.

AB - Writing is challenging, especially for non-native speakers. To support English as a Second Language (ESL) writing, we propose StructFeed, which allows native speakers to annotate topic sentence and relevant keywords in texts and generate writing hints based on the principle of paragraph unity. First, we compared our crowd-based method with three na¨ıve machine learning (ML) methods and got the best performance on the identiﬁcation of topic sentence and irrelevant sentence in the article. Next, we evaluated the StructFeed system with two feedback-generation mechanisms including feedback generated by one expert and by one crowd worker. The results showed that people who received feedback by StructFeed got the highest improvement after revision.

M3 - Conference contribution

SP - 71

EP - 78

BT - Proceedings of the AAAI Conference on Human Computation and Crowdsourcing

ER -

Supporting ESL Writing by Prompting Crowdsourced Structural Feedback.

Abstract

Access to Document

Fingerprint

Cite this