A Dependency Graph-Based Keyphrase Extraction Method Using Anti-patterns
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Keyphrase extraction is one of fundamental natural language processing (NLP) tools to improve many textminingapplications such as document summarization and clustering. In this paper, we propose to use twonovel techniques on the top of the state-of-the-art keyphrase extraction methods. First is the anti-patternsthat aim to recognize non-keyphrase candidates. The state-of-the-art methods often used the rich feature setto identify keyphrases while those rich feature set cover only some of all keyphrases because keyphrases sharevery few similar patterns and stylistic features while non-keyphrase candidates often share many similarpatterns and stylistic features. Second one is to use the dependency graph instead of the word co-occurrencegraph that could not connect two words that are syntactically related and placed far from each other in asentence while the dependency graph can do so. In experiments, we have compared the performances withdifferent settings of the graphs (co-occurrence and dependency), and with the existing method results. Finally, we discovered that the combination method of dependency graph and anti-patterns outperform thestate-of-the-art performances.
Abstract
Keyphrase extraction is one of fundamental natural language processing (NLP) tools to improve many textminingapplications such as document summarization and clustering. In this paper, we propose to use twonovel techniques on the top of the state-of-the-art keyphrase extraction methods. First is the anti-patternsthat aim to recognize non-keyphrase candidates. The state-of-the-art methods often used the rich feature setto identify keyphrases while those rich feature set cover only some of all keyphrases because keyphrases sharevery few similar patterns and stylistic features while non-keyphrase candidates often share many similarpatterns and stylistic features. Second one is to use the dependency graph instead of the word co-occurrencegraph that could not connect two words that are syntactically related and placed far from each other in asentence while the dependency graph can do so. In experiments, we have compared the performances withdifferent settings of the graphs (co-occurrence and dependency), and with the existing method results. Finally, we discovered that the combination method of dependency graph and anti-patterns outperform thestate-of-the-art performances.
참고문헌 (28)
- T. Munkhdalai, "Incorporating domain knowledge in chemical and biomedical named entity recognition with word representations", Journal of Cheminformatics, 7(Suppl 1) (2015)
- K. H. Ryu, "Biomedical text mining: an overview and an examplary application", Proceedings of International Conference on Information and Convergence Technology for Smart Society (ICICTS) (2015)
- T. Munkhdalai, "Towards a unified named entity recognition system", Proceedings of the International Joint Conference on Biomedical Engineering Systems and Technologies, pp.251~255 (2015)
- M. Li, "A novel approach for protein-named entity recognition and protein-protein interaction extraction", Mathematical Problems in Engineering, 2015 (2015)
- E. Batbaatar, "Incorporating domain knowledge in chemical named entity recognition using deep learning", Proceedings of 2016 International Conference on Information, System and Convergence Application (2016)
- P. D. Turney, "Learning algorithms for keyphrase extraction", Information Retrieval, 2(4), pp.303~336 (2000)
- Kamal Sarkar, "Machine Learning Based Keyphrase Extraction: Comparing Decision Trees, Naïve Bayes, and Artificial Neural Networks", JIPS(Journal of Information Processing Systems), 8(4), pp.693~712 (2012), 한국정보처리학회[DOI]
- J. Wang, "Advances in Machine Learning and Cybernetics", pp.633~641 (2006), Springer
- I. H. Witten, "KEA: practical automated keyphrase extraction", Proceedings of the 4th ACM Conference on Digital Libraries, pp.254~255 (1999)
- O. Medelyan, "Thesaurus based automatic keyphrase indexing", Proceedings of the 6th ACM, 2006, 296~297
- R. Mihalcea, "Textrank: bringing order into text", Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pp.404~411 (2004)
- S. N. Kim, "SemEval-2010 Task 5: automatic keyphrase extraction from scientific", Proceedings of the 5th International Workshop on Semantic Evaluation, pp.21~26 (2010)
- J. Liu, "Keyword extraction using language network", Proceedings of International Conference on Natural Language Processing and Knowledge Engineering, pp.129~134 (2007)
- X. Wan, "Single document keyphrase extraction using neighborhood knowledge", Proceedings of the 23rd AAAI Conference on Artificial Intelligence, pp.855~860 (2008)
- Z. Liu, "Automatic keyphrase extraction via topic decomposition", Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp.366~376 (2010)
- D. M. Blei, "Latent Dirichlet allocation", Journal of Machine Learning Research, 3, pp.993~1022 (2003)
- W. X. Zhao, "Topical keyphrase extraction from twitter", Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp.379~388 (2011)
- A. Bellaachia, "Ne-rank: a novel graph-based keyphrase extraction in twitter", Proceedings of the 2012 IEEE, ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology, pp.2012[DOI]
- A. Hulth, "Improved automatic keyword extraction given more linguistic knowledge", Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, pp.216~223 (2003)
- T. D. Nguyen, "Keyphrase extraction in scientific publications", Proceedings of International Conference on Asian Digital Libraries, pp.317~326 (2007)
- J. Hipp, "Algorithms for association rule mining: a general survey and comparison", ACM SIGKDD Explorations Newsletter, 2(1), pp.58~64 (2000)
- M. Rafiqul Islam, "An improved keyword extraction method using graph based random walk model", Proceedings of the 11th International Conference on Computer and Information Technology, pp.225~229 (2008), IEEE
- K. S. Hasan, "Conundrums in unsupervised keyphrase extraction: making sense of the state-ofthe-art", Proceedings of the 23rd International Conference on Computational Linguistics: Posters, pp.365~373 (2010)
- Z. Zhu, "Combination of unsupervised keyphrase extraction algorithms", Proceedings of 2013 International Conference on Asian Language Processing (IALP), pp.33~36 (2013)
- D. Klein, "Accurate unlexicalized parsing", Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, pp.423~430 (2003)
- D. Klein, "Fast exact inference with a factored model for natural language parsing", Advances in Neural Information Processing Systems, 15, pp.3~10 (2003)
- De Marneffe, "Generating typed dependency parses from phrase structure parses", Proceedings of LREC, 6, pp.449~454 (2006)
- S. Hassan, "Random walk term weighting for improved text classification", Proceedings of 2006 Workshop on Graph-based Methods for Natural Language Processing, pp.53~60 (2006)