Various online writing assistance tools have been developed through efforts in the areas of Natural Language Processing, such as online thesaurus, web-based concordance tools, automatic essay scorer (e.g., My Access, Criterion). Their effectiveness when applied in language classrooms may vary depending on their functional rigor and pedagogical designs. In this paper, we introduce how we develop a computer program that can provide suggestions when learner writers are composing abstracts online. A computer system, WriteAhead, provides learner writers with writing suggestions from a specific discipline on a web-based platform, in order to assist their abstract writing. The method involves automatically building domain-specific corpora of abstracts from the web via domain names and related keywords as query expansions, and automatically extracting vocabulary and n-grams in order to offer writing suggestions from the corpora. At runtime, learner writers' input in the writing area of the system actively triggers a set of corresponding writing suggestions. This prototype abstract writing assistant system, WriteAhead, facilitates interactions between learners and system for writing abstracts in an effective and contextualized way. For assessment of WriteAhead, we conducted an experiment with two groups of graduate students, each group wrote an abstract with the system and the other without the system. Surveys were conducted for the assessment, along with evaluations and qualitative analysis on the abstracts. Findings and implications show that most students are satisfied with WriteAhead in most aspects of writing suggestion, and that students can effectively compose abstracts with qualities via the system.

近年來，有許多線上寫作輔助工具透過自然語言處理的技術陸續問世，如線上字典、字詞檢索工具、文章自動評分工具等等。這些工具的效能會因為他們強調的功能特性或是在教育方法上的設計差異而有所不同。在本論文中，我們設計了一個線上摘要寫作輔助系統，當使用者寫摘要的時候，系統可以自動提供使用者寫作建議。我們將這個系統命名為WriteAhead。為了要自動提供使用者寫作建議，這個系統會根據使用者選擇的學術領域，自動從相對應的語料庫中找出相關的寫作建議。我們設計這個系統的方法包含了以下幾點：第一、本方法以各領域名稱以及其相關的關鍵字當作網路檢索的查詢詞組，從網路中自動建立各領域的摘要語料庫；第二、本方法從語料庫中自動取出相關的字詞與N-Gram作為寫作建議；第三、使用者在實際寫作時，本方法將使用者的最後輸入的幾個字詞自動視為查詢的關鍵詞組，在語料庫中找尋可能相對應的寫作建議。我們的這個WriteAhead輔助寫作系統可以有效提升使用者和輔助寫作工具之間的互動性。為了評估WriteAhead的效能，我們以學術論文寫作課程的兩班的研究生進行實驗，評估有無使用WriteAhead的狀況下，摘要寫作的表現。我們另外也讓參與實驗的學生填寫問卷，透過問卷的結果瞭解他們對於WriteAhead的看法，另外也透過分析摘要內容來分析有無使用WriteAhead的差異。實驗結果顯示大多數的學生對於WriteAhead提供的寫作建議感到滿意，同時學生也利用這個系統進行摘要寫作，提高了寫作的效率與品質。

Table of Contents
摘要...............................................................................................................................................................i
ABSTRACT..................................................................................................................................................ii
致謝辭.........................................................................................................................................................iii
Table of Contents.........................................................................................................................................iv
List of Tables................................................................................................................................................v
List of Figures.............................................................................................................................................vii
Chapter 1 Introduction............................................................................................................................1
Chapter 2 Related Work...........................................................................................................................4
Chapter 3 WriteAhead System...............................................................................................................13
3.1 Problem Statement...................................................................................................................13
3.2 Generating Writing Suggestions..............................................................................................15
(3.2.1) Build Discipline-Specific Corpora from the Web..........................................................16
(3.2.2) Generating Writing Suggestions and Tagged Data from the Corpora...........................17
(3.2.3) Generating Writing Suggestions from Tagged Data......................................................19
(3.3.4) Generating Output Database for Writing Suggestions...................................................23
3.3 Writing Suggestions at Run Time...........................................................................................25
Chapter 4 Experimental Settings............................................................................................................26
4.1 Training WriteAhead...............................................................................................................26
4.2 Experimental Setup and Evaluation Metrics...........................................................................34
Chapter 5 Results and Discussion..........................................................................................................37
5.1 Results from the Questionnaire..............................................................................................37
5.2 Results from the Video...........................................................................................................42
5.3 Content Analysis and Error Analysis.....................................................................................44
5.4 Scoring Result of the Two Raters..........................................................................................46
Chapter 6 Future Work and Conclusion................................................................................................47
Rerferences.................................................................................................................................................48
Appendix A – Two Writing Tasks............................................................................................................51
Appendix B – Questionnaire Format........................................................................................................52
Appendix C – Suggestion from the Questionnaire...................................................................................53
Appendix D – List of Collocation Errors..................................................................................................54

Allison, D., Cooley, L., Lewkowicz, J., & Nunan, D. (1998). Dissertation writing in action: The development of a dissertation writing support program for ESL graduate research students. English for Specific Purposes, 17(2), 199–217.

Burstein, J., Chodorow, M., & Leacock, C. (2003). Criterion: Online essay evaluation: An application for automated evaluation of student essays. In Proceedings of the fifteenth annual conference on innovative applications of artificial intelligence. Acapulco, Mexico.

Cobb, T., Greaves, C. and Horst, M. (2001). ‘Can the rate of lexical acquisition from reading be increased? An experiment in reading French with a suite of online resources’ in P. Raymond and C. Cornaire (eds.) Regards sur la didactique des langues secondes. Montr□al: □ditions Logique.

Carvalho, V. R.& Cohen, W. W. (2006). Improving “Email Speech Acts” Analysis via N-gram Selection. In Proceedings of the Analyzing Conversations in Text and Speech (ACTS) Workshop at HLT-NAACL. 35–41, New York City, New York, USA.

Chan, S.K., & Foo, S. (2006). Application of Explicit Knowledge (EK) in an Abstract Writing Experience (AWE). In Proceedings of 5th Language for Specific Purposes International Seminar: LSP: Exploring New Frontiers. Johor Bahru, Malaysia.

Crystal, A. (2003). Interface Design for Metadata Creation. In Proceedings of the Conference on Human Factors in Computing Systems, 1038-1039. Florida, USA: Ft. Lauderdale.

Curado Fuentes, A. (2001). Lexical Behaviour in Academic and Technical Corpora: Implications for ESP Development, Language Learning & Technology, Vol.5, 106-129.

Dong, Y. (1998). Non-native graduate students’thesis/dissertation writing in science: Self-reports by students and their advisors from two US institutions. English for Specific Purposes, 17(4), 369–390.

Fuentes, A. C. (2006). Doctorate writing evaluation in the EAP setting: a corpus-based analysis. Proceedings of the 5th International AELFE Conference, 623-628. Zaragoza, Spain: Escuela Universitaria de Ingenier□a T□cnica Industrial.

Genoves L., Feltrim V. D., Dayrell C., Alusio S. (2007). Automatically detecting schematic structure components of English abstracts: building a high accuracy classifier for the task. In Proceedings of Recent Advances in Natural Language Processing (RANLP2007): International Workshop on Natural Language Processing for Educational Resources, Borovets, Bulgaria, 27-29.

Gledhill, C. (2000). The Discourse Function of Collocation in Research Article Introductions. English for Specific Purposes, 19, 115-135.

Howarth, P. (1996). Phraseology in English Academic Writing. Tubingen: Max Niemeyer Verlag.

Jian, J. Y., Chang, Y. C. and Chang, J. S. (2004). TANGO: Bilingual collocational concordancer. In Proceedings of ACL on Interactive poster and demonstration sessions. Barcelona, Spain.

Krishnamurthy, R., Kosem, I. (2007). Issues in creating a corpus for EAP pedagogy and research. English for Academic Purposes, 6, 356–373.

Lin, Y. H., Chen, M. H., Wu, J. C. and Chang, J. S. (2009) Automatically Identify Sections in Academic Abstracts. In Proceedings of 2009 International Conference on Applied Linguistics & Language Teaching (ALLT). Taipei, Taiwan: National Taiwan University of Science and Technology, 357-368.

Nattinger, J. R., & DeCarrico, J. S. (1992). Lexical Phrases and Language Teaching. Oxford: Oxford University Press.

Och, F. J. (1999). An Efficient Method for Determining Bilingual Word Classes. In Ninth Conference of the European Chapter of the Association for Computational Linguistics (EACL'99), 71-76.

Scott, M., (1996), Wordsmith Tools, Oxford: Oxford University Press. ISBN 0-19-458984-6.

Sinclair, J. (1991). Corpus, Concordance, Collocation. Hong Kong: Oxford University Press.

Sun, Y. C. (2007). Learner perceptions of a concordancing tool for academic writing. Computer-Assisted Language Learning, 20(4), 323-343.

Swales, J. (1990). Genre Analysis: English in Academic and Research Settings. Cambridge: Cambridge University Press.

Teufel, S., Moens, M. (2002). Summarizing scientific articles —experiments with relevance and rhetorical status. Computational Linguistics 28, 409-446.

Weaver, G., Strickland, B., and Crane, G. (2006). Quantifying the accuracy of relational statements in Wikipedia: a methodology. In Proceedings of ACM/IEEE Joint Conference on Digital Libraries, 358–358. Chapel Hill, NC, USA.

Tsuruoka, Y. and Tsujii, J. (2005). Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data, In Proceedings of HLT/EMNLP 2005, 467-474.

楊永林 (Yang, 2000)。 EAME：一種基於問句驅動、鏡像模擬基礎之上的文本生成系統。《現代外語》3，296-305。