本論文提出一個透過Collins COBUILD的文法規則推導名詞參數的語義分類的方法，以協助英語學習者在寫作過程獲得文法規則相關的提示。
我們將文法規則轉換成語料搜尋引擎的查詢式並檢索N-gram，再透過WordNet取得名詞參數之岐義資訊，計算文法規則之名詞參數
語料搜索引擎的N-gram與WordNet的詞義為每個文法規則的名詞參數產生語義分類。
此方法涉及把文法規則轉換成語料搜尋引撆的查詢式、檢索N-gram與詞義、篩選候選字，以及透過演算法計算分數。

我們提出了一個寫作輔助系統Composer，把此方法應用在Collins COBUILD文法規則及Google Web 1T語料上。
實驗結果顯示，本系統能推導出有效且對學習者有用的語義及文法資訊。

This paper describes a method for deriving semantic categories for noun argument in a given grammar pattern of a head word.
In our approach, we use ngrams retrieved from Web-scale ngram and WordNet supersenses to generates all possible candidates.
The method involves converting the grammar pattern into an effective regular expression query, retrieving ngrams from the given grams, generates and sense disambiguating norminal argument.

We present a prototype system, Composer that applies the proposed method to a set of manually compiled grammar patterns and Google Web 1T.
The preliminary evaluation shows the system derives reasonably well semantics categories, which are useful for learning vocabulary and grammar.

Abstract i
摘要 ii
致謝 iii
Contents iv
List of Figures vi
List of Tables vii
1 Introduction 1
2 Related Work 5
3 Methodology 8
3.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.2 Generate Queries and Derive Semantic Categories from N-grams . . 9
3.2.1 Transform Grammar Patterns Into Queries . . . . . . . . . . 10
3.2.2 Retrieve N-grams from Linggle . . . . . . . . . . . . . . . . 10
3.2.3 Adjunct Detection . . . . . . . . . . . . . . . . . . . . . . . 12
3.2.4 Derive Semantic Categories with WordNet Supersenses . . . 14
3.3 Run-time Interactive System . . . . . . . . . . . . . . . . . . . . . . 16
4 Experiment and Evaluation 18
4.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
4.1.1 Collins COBUILD Grammar Pattern . . . . . . . . . . . . . 18
4.1.2 Academic Keyword List . . . . . . . . . . . . . . . . . . . . 19
4.2 Experimental Settings . . . . . . . . . . . . . . . . . . . . . . . . . 19
4.3 Evaluation Results . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
5 Conclusion and Future Work 23
Reference 25

1. Naoki Abe and Hang Li. Learning word association norms using tree cut pair models. arXiv preprint cmp-lg/9605029, 1996.

2. Omri Abend and Ari Rappoport. Fully unsupervised core-adjunct argument classification. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 226-236, 2010.

3. Carsten Brockmann and Mirella Lapata. Evaluating and combining approaches to selectional preference acquisition. In 10th Conference of the European Chapter of the Association for Computational Linguistics, 2003.

4. Stephen Clark and David Weir. Class-based probability estimation using a semantic hierarchy. Computational Linguistics, 28(2):187-206, 2002.

5. Katrin Erk. A simple, similarity-based model for selectional preferences. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 216-223, 2007.

6. Daniel Gildea and Daniel Jurafsky. Automatic labeling of semantic roles. Computational linguistics, 28(3):245-288, 2002.

7. Marti A Hearst. Can natural language processing become natural language coaching? 2015.

8. Donald Hindle and Mats Rooth. Structural ambiguity and lexical relations. Computational linguistics, 19(1):103-120, 1993.


9. Najoung Kim, Kyle Rawlins, Benjamin Van Durme, and Paul Smolensky. Predicting the argumenthood of english prepositional phrases. In Proceedings of the AAAI Conference on Articial Intelligence, volume 33, pages 6578-6585, 2019.


10. Mitchell Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. Building a large annotated corpus of english: The penn treebank. 1993.


11. George A Miller. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39-41, 1995.


12. Patrick Pantel, Rahul Bhagat, Bonaventura Coppola, Timothy Chklovski, and Eduard Hovy. Isp: Learning inferential selectional preferences. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pages 564-571, 2007.


13. Philip Resnik. Selectional constraints: An information-theoretic model and its computational realization. Cognition, 61(1-2):127-159, 1996.


14. Philip Resnik. Selectional preference and sense disambiguation. In Tagging Text with Lexical Semantics: Why, What, and How?, 1997.


15. Basili Roberto, Diego De Cao, Paolo Marocco, and Marco Pennacchiotti. Learning selectional preferences for entailment or paraphrasing rules. In In RANLP, 2007.


16. Karin Kipper Schuler. Verbnet: A broad-coverage, comprehensive verb lexicon., 2005.