@inproceedings{3747, author = {{Al Khatib, Khalid and Wachsmuth, Henning and Kiesel, Johannes and Hagen, Matthias and Stein, Benno}}, booktitle = {{Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers}}, pages = {{3433--3443}}, title = {{{A News Editorial Corpus for Mining Argumentation Strategies}}}, year = {{2016}}, } @inproceedings{3801, author = {{Al-Khatib, Khalid and Wachsmuth, Henning and Hagen, Matthias and Köhler, Jonas and Stein, Benno}}, booktitle = {{Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}}, pages = {{1395--1404}}, title = {{{Cross-Domain Mining of Argumentative Text through Distant Supervision}}}, doi = {{10.18653/v1/N16-1165}}, year = {{2016}}, } @inproceedings{3816, author = {{Wachsmuth, Henning and Al Khatib, Khalid and Stein, Benno}}, booktitle = {{Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers}}, isbn = {{978-3-88579-975-7}}, pages = {{1680--1691}}, title = {{{Using Argument Mining to Assess the Argumentation Quality of Essays}}}, year = {{2016}}, } @inproceedings{3880, author = {{Wachsmuth, Henning}}, booktitle = {{Ausgezeichnete Informatikdissertationen 2015}}, isbn = {{978-3-88579-975-7}}, pages = {{329--338}}, title = {{{Pipelines Für Effiziente und Robuste Ad-hoc Textanalyse}}}, year = {{2016}}, } @inproceedings{14881, author = {{Chen, Wei-Fan and Ku, Lun-Wei}}, booktitle = {{Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics}}, pages = {{1635--1645}}, title = {{{UTCNN: a Deep Learning Model of Stance Classification on Social Media Text}}}, year = {{2016}}, } @inproceedings{14882, author = {{Chen, Wei-Fan and Lin, Fang-Yu and Ku, Lun-Wei}}, booktitle = {{Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations}}, pages = {{273--277}}, title = {{{WordForce: Visualizing Controversial Words in Debates}}}, year = {{2016}}, } @inproceedings{14883, author = {{Ku, Lun-Wei and Chen, Wei-Fan}}, booktitle = {{Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Tutorial Abstracts}}, pages = {{5--8}}, title = {{{Chinese Textual Sentiment Analysis: Datasets, Resources and Tools}}}, year = {{2016}}, } @inproceedings{3815, author = {{Wachsmuth, Henning and Kiesel, Johannes and Stein, Benno}}, booktitle = {{Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing}}, editor = {{Tsujii, Junichi and Hajic, Jan}}, isbn = {{978-3-319-25740-2}}, pages = {{601--611}}, title = {{{Sentiment Flow - A General Model of Web Review Argumentation}}}, doi = {{10.18653/v1/D15-1072}}, year = {{2015}}, } @book{3879, author = {{Wachsmuth, Henning}}, isbn = {{978-3-319-25740-2}}, title = {{{Text Analysis Pipelines - Towards Ad-hoc Large-scale Text Mining}}}, doi = {{http://dx.doi.org/10.1007/978-3-319-25741-9}}, year = {{2015}}, } @phdthesis{7568, abstract = {{Today's web search and big data analytics applications aim to address information needs~(typically given in the form of search queries) ad-hoc on large numbers of texts. In order to directly return relevant information instead of only returning potentially relevant texts, these applications have begun to employ text mining. The term text mining covers tasks that deal with the inference of structured high-quality information from collections and streams of unstructured input texts. Text mining requires task-specific text analysis processes that may consist of several interdependent steps. These processes are realized with sequences of algorithms from information extraction, text classification, and natural language processing. However, the use of such text analysis pipelines is still restricted to addressing a few predefined information needs. We argue that the reasons behind are three-fold: First, text analysis pipelines are usually made manually in respect of the given information need and input texts, because their design requires expert knowledge about the algorithms to be employed. When information needs have to be addressed that are unknown beforehand, text mining hence cannot be performed ad-hoc. Second, text analysis pipelines tend to be inefficient in terms of run-time, because their execution often includes analyzing texts with computationally expensive algorithms. When information needs have to be addressed ad-hoc, text mining hence cannot be performed in the large. And third, text analysis pipelines tend not to robustly achieve high effectiveness on all texts, because their results are often inferred by algorithms that rely on domain-dependent features of texts. Hence, text mining currently cannot guarantee to infer high-quality information. In this thesis, we contribute to the question of how to address information needs from text mining ad-hoc in an efficient and domain-robust manner. We observe that knowledge about a text analysis process and information obtained within the process help to improve the design, the execution, and the results of the pipeline that realizes the process. To this end, we apply different techniques from classical and statistical artificial intelligence. In particular, we first develop knowledge-based approaches for an ad-hoc pipeline construction and for an optimal execution of a pipeline on its input. Then, we show theoretically and practically how to optimize and adapt the schedule of the algorithms in a pipeline based on information in the analyzed input texts in order to maximize execution efficiency. Finally, we learn patterns in the argumentation structures of texts statistically that remain strongly invariant across domains and that, thereby, allow for more robust analysis results in a restricted set of tasks. We formally analyze all developed approaches and we implement them as open-source software applications. Based on these applications, we evaluate the approaches on established and on newly created collections of texts for scientifically and industrially important text analysis tasks, such as financial event extraction and fine-grained sentiment analysis. Our findings show that text analysis pipelines can be designed automatically, which process only portions of text that are relevant for the information need at hand. Through scheduling, the run-time efficiency of pipelines can be improved by up to more than one order of magnitude while maintaining effectiveness. Moreover, we provide evidence that a pipeline's domain robustness substantially benefits from focusing on argumentation structure in tasks like sentiment analysis. We conclude that our approaches denote essential building blocks of enabling ad-hoc large-scale text mining in web search and big data analytics applications.}}, author = {{Wachsmuth, Henning}}, title = {{{Pipelines for Ad-hoc Large-scale Text Mining}}}, year = {{2015}}, } @inproceedings{14875, author = {{Chen, Wei-Fan and Chen, MeiHua and Ku, Lun-Wei}}, booktitle = {{Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications}}, pages = {{144--153}}, title = {{{Embarrassed or Awkward? Ranking Emotion Synonyms for ESL Learners’ Appropriate Wording}}}, year = {{2015}}, } @inproceedings{14877, author = {{Chen, Wei-Fan and Ku, Lun-Wei and Lee, Yann-Hui}}, booktitle = {{2015 AAAI Spring Symposium Series}}, title = {{{Mining Supportive and Unsupportive Evidence from Facebook Using Anti-reconstruction of the Nuclear Power Plant as an Example}}}, year = {{2015}}, } @inproceedings{14878, author = {{Chen, Wei-Fan and Lee, Yann-Hui and Ku, Lun-Wei}}, booktitle = {{International Conference on HCI in Business}}, pages = {{22--33}}, title = {{{Topic-based Stance Mining for Social Media Texts}}}, year = {{2015}}, } @article{14879, author = {{Chen, Wei-Fan and Chen, Mei-Hua and Chen, Ming-Lung and Ku, Lun-Wei}}, journal = {{IEEE Transactions on Knowledge and Data Engineering}}, number = {{5}}, pages = {{1093--1104}}, publisher = {{IEEE}}, title = {{{A Computer-assistance Learning System for Emotional Wording}}}, volume = {{28}}, year = {{2015}}, } @inproceedings{14876, author = {{Chen, Mei-Hua and Chen, Wei-Fan and Ku, Lun-Wei}}, booktitle = {{Proceedings of the sixth joint Foreign Language Education and Technology Conference (FLEAT VI)}}, title = {{{Technology Enhanced Emotion Expression Learning}}}, year = {{2015}}, } @inproceedings{20142, author = {{Wachsmuth, Henning and Trenkmann, Martin and Stein, Benno and Engels, Gregor and Palakarska, Tsvetomira}}, booktitle = {{Proceedings of the 15th International Conference on Intelligent Text Processing and Computational Linguistics}}, pages = {{115–127}}, title = {{{A Review Corpus for Argumentation Analysis}}}, year = {{2014}}, } @inproceedings{3805, author = {{Brüseke, Frank and Wachsmuth, Henning and Engels, Gregor and Becker, Steffen}}, booktitle = {{Proceedings of the 4th International Symposium on Autonomous Minirobots for Research and Edutainment}}, number = {{12}}, pages = {{1975--2004}}, title = {{{PBlaman: performance blame analysis based on Palladio contracts}}}, year = {{2014}}, } @inproceedings{3877, author = {{Wachsmuth, Henning and Trenkmann, Martin and Stein, Benno and Engels, Gregor}}, booktitle = {{Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers}}, pages = {{553--564}}, title = {{{Modeling Review Argumentation for Robust Sentiment Analysis}}}, year = {{2014}}, } @article{3905, author = {{Abu Quba Rana, Chamsi and Hassas, Salima and Usama, Fayyad and Alshomary, Milad and Gertosio, Christine}}, journal = {{2014 IEEE/ACS 11th International Conference on Computer Systems and Applications (AICCSA)}}, pages = {{169--175}}, title = {{{iSoNTRE: The Social Network Transformer into Recommendation Engine}}}, year = {{2014}}, } @inproceedings{14874, author = {{Chen, Mei-Hua and Chen, Wei-Fan and Ku, Lun-Wei}}, booktitle = {{Proceedings of the AsiaCALL 2014}}, title = {{{RESOLVE: An Emotion Word Suggestion System Facilitates Language Learners’ Emotional Expressions}}}, year = {{2014}}, }