A modular system for support of experiments in text classification

Michal Ptaszynski

Abstrakt

This paper presents a modular system for the support of experiments and research in text classification. Usually the research process requires two general kinds of abilities. Firstly, to laboriously analyse the provided data, perform experiments and from the experiment results create materials for preparing a scientific paper such as tables or graphs. The second kind of task includes, for example, providing a creative discussion of the results. To help researchers and allow them to focus more on creative tasks, we provide a system which helps performing the laborious part of research. The system prepares datasets for experiments, automatically performs the experiments and from the results calculates the scores of Precision, Recall, F-score, Accuracy, Specificity and phi-coefficient. It also creates tables in the LaTex format containing all the results and it draws graphs depicting and informatively comparing each group of results.

Słowa kluczowe: Experiment support, Pattern extraction, Graph generation
References

[1] Hidetsugu Nanba, Noriko Kando, Manabu Okumura, Classification of research papers using citation links and citation types: Towards automatic review article generation, [in:] Proceedings of 11th ASIS SIG/CR Classification Research Workshop, 2000, 117-134.

[2] Tomohide Shibata, Sadao Kurohashi, Automatic slide generation based on discourse structure analysis, [in:] Proceedings of IJCNLP, Springer Berlin Heidelberg, 2005, 754-766.

[3] Ptaszynski M., Fumito Masui, Rzepka R., Kenji Araki, Automatic Extraction of Emotive and Non-emotive Sentence Patterns, [In:] Proceedings of The Twentieth Annual Meeting of The Association for Natural Language Processing (NLP2014), Sapporo, Japan, 2014, 868-871.

[4] Ptaszynski M., Fumito Masui, Rzepka R., Kenji Araki, Emotive or Non-emotive: That is The Question, [in:] Proceedings of 5th Workhsop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA 2014), Baltimore, USA, 2014, 59-65, held in conjunction with The 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), June 22–27.

[5] Ptaszynski M., Fumito Masui, Rzepka R., Kenji Araki, Detecting emotive sentences with pattern-based language modelling, [in:] Proceedings of the 18th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems − KES2014, 484-493, Gdynia, Poland 2014.

[6] Ptaszynski M., Dai Hasegawa, Fumito Masui, Hiroshi Sakuta, Eijiro Adachi, How Differently Do We Talk? A Study of Sentence Patterns in Groups of Different Age, Gender and Social Status, [in:] Proceedings of The Twentieth Annual Meeting of The Association for Natural Language Processing (NLP2014), Sapporo, Japan 2014, 3-6.

[7] Ptaszynski M., Dai Hasegawa, Fumito Masui, Women Like Backchannel, But Men Finish Earlier: Pattern Based Language Modeling of Conversations Reveals Gender and Social Distance Differences, [in:] Samsung HLT Young Researchers Symposium, 9th International Conference on Natural Language Processing (PolTAL 2014), paper ID: 02, Warszawa, Poland 2014.

[8] Yoko Nakajima, Ptaszynski M., Hirotoshi Honma, Fumito Masui, Investigation of Future Reference Expressions in Trend Information, [in:] Proceedings of the 2014 AAAI Spring Symposium Series, “Big data becomes personal: knowledge into meaning For better health, wellness and well-being”, Stanford, USA 2014, 31-38.

[9] Yoko Nakajima, Ptaszynski M., Hirotoshi Honma, Fumito Masui, Extraction of Future Reference Expressions in Trend Information, [in:] The Proceedings of 24th Intelligent System Symposium (FAN2014), Kitami, Japan 2014.

[10] Potts Ch., Schwarz F., Exclamatives and heightened emotion: Extracting pragmatic generalizations from large corpora, Ms., UMass Amherst, 2008. 242