Graph-Based Complex Representation in Inter-Sentence Relation Recognition in Polish Texts

Janz, Arkadiusz; Kędzia, Paweł; Piasecki, Maciej

doi:10.2478/cait-2018-0013

Abstract

This paper presents a supervised approach to the recognition of Cross-document Structure Theory (CST) relations in Polish texts. Its core is a graph-based representation constructed for sentences. Graphs are built on the basis of lexicalised syntactic-semantic relations extracted from text. Similarity between sentences is calculated as similarity between their graphs, and the values are used as features to train the classifiers. Several different configurations of graphs, as well as graph similarity methods were analysed for this task. The approach was evaluated on a large open corpus annotated manually with 17 types of selected CST relations. The configuration of experiments was similar to those known from SEMEVAL and we obtained very promising results.

References

1. Aleixo, P., T. A. S. Pardo. Finding Related Sentences in Multiple Documents for Multidocument Discourse Parsing of Brazilian Portuguese Texts. – In: Companion Proc. of XIV Brazilian Symposium on Multimedia and the Web, WebMedia’08, New York, USA, 2008, ACM, pp. 298-303.10.1145/1809980.1810055
Search in Google Scholar Back to article
2. Broda, B., M. Marcińczuk, M. Maziarz, A. Radziszewski, A. Wardyński. KPWr: Towards a Free Corpus of Polish. – In: Proc. of 8th International Conference on Language Resources and Evaluation (LREC’12), Istanbul, Turkey, May 2012, European Language Resources Association (ELRA), Nicoletta Calzolari (Conference Chair), Khalid Choukri, Thierry Declerck, Mehmet Uğur Doğan, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis, Eds.
Search in Google Scholar Back to article
3. Broda, B., P. Kędzia, M. Marcińczuk, A. Radziszewski, R. Ramocki, A. Wardyński. Fextor: A Feature Extraction Framework for Natural Language Processing: A Case Study in Word Sense Disambiguation, Relation Recognition and Anaphora Resolution. – In: Computational Linguistics: Applications. Adam Przepiórkowski, Maciej Piasecki, Krzysztof Jassem, Piotr Fuglewicz, Eds. Berlin, Heidelberg, Springer, 2013, pp. 41-62.10.1007/978-3-642-34399-5_3
Open DOI Search in Google Scholar Back to article
4. Bunke, H. On a Relation between Graph Edit Distance and Maximum Common Subgraph. – Pattern Recogn. Lett., Vol. 18, August 1997, No 9, pp. 689-694.10.1016/S0167-8655(97)00060-3
Open DOI Search in Google Scholar Back to article
5. Bunke, H., K. Shearer. A Graph Distance Metric Based on the Maximal Common Subgraph. – Pattern Recogn. Lett., Vol. 19, March 1998, No 3-4, pp. 255-259.10.1016/S0167-8655(97)00179-7
Open DOI Search in Google Scholar Back to article
6. Cardoso, P. C. F., E. G. Maziero, M. L. C. Jorge, E. R. M. Seno, A. Di Felippo, L. H. M. Rino, M. das G. V. Nunes, T. A. S. Pardo. CSTNews – A Discourseannotated Corpus for Single and Multi-Document Summarization of News Texts in Brazilian Portuguese. – In: Proc. of 3rd RST Brazilian Meeting, Cuiabá, Brazil, 2011, pp. 88-105.
Search in Google Scholar Back to article
7. Fernández, M.-L., G. Valiente. A Graph Distance Metric Combining Maximum Common Subgraph and Minimum Common Supergraph. – Pattern Recogn. Lett., Vol. 22, May 2001, No 6-7, pp. 753-758.10.1016/S0167-8655(01)00017-4
Open DOI Search in Google Scholar Back to article
8. Harary, F., R. C. Read. Is the Null-Graph a Pointless Concept? – In: Lecture Notes in Mathematics. Vol. 406. 1974, pp. 37-44.10.1007/BFb0066433
Search in Google Scholar Back to article
9. Jaccard, P. The Distribution of the Flora in the Alpine Zone. – New Phytologist, Vol. 11, February 1912, No 2, pp. 37-50.10.1111/j.1469-8137.1912.tb05611.x
Open DOI Search in Google Scholar Back to article
10. Kędzia, P., M. Maziarz. Recognizing Semantic Relations within Polish Noun Phrase: A Rule-Based Approach. – In: RANLP, 2013.
Search in Google Scholar Back to article
11. Kohavi, R. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. – In: Proc. of 14th International Joint Conference on Artificial Intelligence IJCAI’95, San Francisco, CA, USA, 1995. Morgan Kaufmann Publishers, Inc., Vol. 2, pp. 1137-1143.
Search in Google Scholar Back to article
12. Kumar, Y. J., N. Salim, A. Hamza, A. Abuobieda. Automatic Identification of Cross-Document. – Structural Relationships, Vol. 7, 2012, pp. 26-29.10.1109/InfRKM.2012.6204977
Search in Google Scholar Back to article
13. Kumar, Y. J., N. Salim, B. Raza. Cross-Document Structural Relationship Identification Using Supervised Machine Learning. – Appl. Soft Comput., Vol. 12, October 2012, No 10, pp. 3124-3131.10.1016/j.asoc.2012.06.017
Search in Google Scholar Back to article
14. Kumar, Y. J., N. Salim, A. Abuobieda, A. T. Albaham. Multi Document Summarization Based on News Components Using Fuzzy Cross-Document Relations. – Applied Soft Computing, Vol. 21, 2014, pp. 265-279.10.1016/j.asoc.2014.03.041
Open DOI Search in Google Scholar Back to article
15. Kędzia, P., M. Piasecki. Ruled-Based, Interlingual Motivated Mapping of plWordNet onto SUMO Ontology. – In: Proc. of 9th International Conference on Language Resources and Evaluation (LREC’14), Reykjavik, Iceland, 26-31 May 2014, Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asunción Moreno, Jan Odijk, Stelios Piperidis, Eds., pp. 4351-4358.
Search in Google Scholar Back to article
16. Kędzia, P., M. Piasecki, J. Kocoń, A. Indyka-Piasecka. Distributionally Extended Network-Based Word Sense Disambiguation in Semantic Clustering of Polish Texts. – IERI Procedia, Vol. 10 (Complete), 2014, pp. 38-44.10.1016/j.ieri.2014.09.073
Search in Google Scholar Back to article
17. Kędzia, P., M. Piasecki, M. Orlińska. Word Sense Disambiguation Based on Large Scale Polish CLARIN Heterogeneous Lexical Resources. – Cognitive Studies/Études Cognitives, Vol. 15, 2015, pp. 269-292. URL: https://ispan.waw.pl/journals/index.php/cs-ec/article/download/cs.2015.019/176510.11649/cs.2015.019
Search in Google Scholar Back to article
18. Landwehr, N., M. Hall, E. Frank. Logistic Model Trees. – Machine Learning, Vol. 59, 2005, No 1, pp. 161-205. ISSN 1573-0565.10.1007/s10994-005-0466-3
Search in Google Scholar Back to article
19. Marcińczuk, M. Automatic Construction of Complex Features in Conditional Random Fields for Named Entities Recognition. – In: RANLP, 2015.
Search in Google Scholar Back to article
20. Marcińczuk, M., J. Kocoń, M. Janicki. Liner2 – A Customizable Framework for Proper Names Recognition for Polish. – In: Intelligent Tools for Building a Scientific Information Platform, Robert Bembenik, Łukasz Skonieczny, Henryk Rybiński, Marzena Kryszkiewicz, Marek Niezgódka, Eds., 2013, pp. 231-253.10.1007/978-3-642-35647-6_17
Search in Google Scholar Back to article
21. Maziarz, M., M. Piasecki, E. Rudnicka, S. Szpakowicz, P. Kędzia. plWordNet 3.0 – A Comprehensive Lexical-Semantic Resource. – In: Proc. of 26th International Conference on Computational Linguistics, COLING 2016, Technical Papers, 11-16 December 2016, Osaka, Japan, pp. 2259-2268.
Search in Google Scholar Back to article
22. Maziero, E. G., M. L. D.-R. C. Jorge, T. A. S. Pardo. Revisiting Cross-Document Structure Theory for Multidocument Discourse Parsing. – Inf. Process. Manage, Vol. 50, March 2014, No 2, pp. 297-314.10.1016/j.ipm.2013.12.003
Search in Google Scholar Back to article
23. Nivre, J., J. Hall, J. Nilsson, A. Chanev, G. Eryigit, S. Kübler, S. Marinov, E. Marsi. MaltParser: A Language-Independent System for Data-Driven Dependency Parsing. – Natural Language Engineering, Vol. 13, 2007, No 2, pp. 95-135.10.1017/S1351324906004505
Search in Google Scholar Back to article
24. Pease, A. Ontology: A Practical Guide. Angwin, CA, Articulate Software Press, 2011.
Search in Google Scholar Back to article
25. Piasecki, M., S. Szpakowicz, B. Broda. A Wordnet from the Ground Up. – Oficyna Wydawnicza Politechniki Wroclawskiej, Wrocław, 2009.
Search in Google Scholar Back to article
26. Piasecki, M., P. Kędzia, M. Orlińska. plWordNet in Word Sense Disambiguation Task. – In: Proc. of 8th Global Wordnet Conference (GWC’16), Bucharest, 27-30 January 2016, Osaka, Japan, pp. 280-290.
Search in Google Scholar Back to article
27. Radev, D. R. A Common Theory of Information Fusion from Multiple Text Sources Step One: Cross-Document Structure. – In: Proc. of 1st SIGdial Workshop on Discourse and Dialogue, SIGDIAL’00, Association for Computational Linguistics, Stroudsburg, PA, USA, Vol. 10, 2000, pp. 74-83.10.3115/1117736.1117745
Search in Google Scholar Back to article
28. Radev, D. R., J. Otterbacher, Z. Zhang. Cst Bank: A Corpus for the Study of Cross-Document Structural Relationships. – In: European Language Resources Association, LREC, 2004.
Search in Google Scholar Back to article
29. Radziszewski, A. A Tiered CRF Tagger for Polish. Springer Berlin Heidelberg, Berlin, Heidelberg, 2013, pp. 215-230. https://doi.org/10.1007/978-3-642-35647-6_1610.1007/978-3-642-35647-6_16
Open DOI Search in Google Scholar Back to article
30. Radziszewski, A., A. Pawlaczek. Language Processing and Intelligent Information Systems. – In: Proc. of 20th International Conference, IIS 2013, Warsaw, Poland, 17-18 June 2013. Chapter Incorporating Head Recognition into a CRF Chunker, Berlin, Heidelberg, Springer, 2013, pp. 22-27.10.1007/978-3-642-38634-3_3
Open DOI Search in Google Scholar Back to article
31. Radziszewski, A., A. Wardyński, T. Śniatowski. WCCL: A Morpho-Syntactic Feature Toolkit. – In: Proc. of Balto-Slavonic Natural Language Processing Workshop (BSNLP’11), Springer, 2011.10.1007/978-3-642-23538-2_55
Search in Google Scholar Back to article
32. Steinwart, I., A. Christmann. Support Vector Machines. First Edition. Springer Publishing Company, Inc., 2008.
Search in Google Scholar Back to article
33. Wallis, W. D., P. Shoubridge, M. Kraetz, D. Ray. Graph Distances Using Graph Union. – Pattern Recogn. Lett., Vol. 22, May 2001, No 6-7, pp. 701-704.10.1016/S0167-8655(01)00022-8
Open DOI Search in Google Scholar Back to article
34. Woliński, M. Morfeusz – A Practical Tool for the Morphological Analysis of Polish. – In: Mieczysław A. Kłopotek, Sławomir T. Wierzchoń, Krzysztof Trojanowski, Eds. Intelligent Information Processing and Web Mining, Advances in Soft Computing, Berlin, Springer, 2006, pp. 503-512.
Search in Google Scholar Back to article
35. Wróblewska, A., M. Woliński. Preliminary Experiments in Polish Dependency Parsing. Berlin, Heidelberg, Springer, 2012, pp. 279-292.10.1007/978-3-642-25261-7_22
Search in Google Scholar Back to article
36. Wróblewska, A. Polish Dependency Parser Trained on an Automatically Induced Dependency Bank. Ph.D. Dissertation, Institute of Computer Science, Polish Academy of Sciences, Warsaw, 2014.
Search in Google Scholar Back to article
37. Zahri, N. A. H. B., F. Fukumoto. Multi-Document Summarization Using Link Analysis Based on Rhetorical Relations between Sentences, Berlin, Heidelberg, Springer, 2011, pp. 328-338.10.1007/978-3-642-19437-5_27
Search in Google Scholar Back to article
38. Zhang, Z., D. Radev. Combining Labeled and Unlabeled Data for Learning Cross-Document Structural Relationships. – In: Proc. of 1st International Joint Conference on Natural Language Processing, Berlin, Heidelberg, Springer, 2005, pp. 32-41.10.1007/978-3-540-30211-7_4
Search in Google Scholar Back to article
39. Zhang, Z., J. Otterbacher, D. Radev. Learning Cross-Document Structural Relationships Using Boosting. – In: Proc. of 12th International Conference on Information and Knowledge Management (CIKM’03), ACM, New York, USA, 2003, pp. 124-130.10.1145/956863.956887
Search in Google Scholar Back to article

Graph-Based Complex Representation in Inter-Sentence Relation Recognition in Polish Texts

Abstract

Paradigm

My account