Filters








8 Hits in 5.3 sec

A Deep Modular RNN Approach for Ethos Mining

Rory Duthie, Katarzyna Budzynska
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
We then develop a novel deep modular recurrent neural network, DMRNN, approach and employ proven methods from argument mining and sentiment analysis to create an ethos mining pipeline.  ...  and negative ethotic sentiment is a powerful instrument for understanding the dynamics of governments.  ...  In order to automatically extract and classify ESEs, we develop an ethos mining pipeline featuring a deep modular recurrent neural network, DMRNN, approach applied for the first time to the NLP task of  ... 
doi:10.24963/ijcai.2018/562 dblp:conf/ijcai/DuthieB18 fatcat:upc47j5wqfhdvjjpljrnu33evu

Exploring the Role of Argument Structure in Online Debate Persuasion [article]

Jialu Li, Esin Durmus, Claire Cardie
2020 arXiv   pre-print
Online debate forums provide users a platform to express their opinions on controversial topics while being exposed to opinions from diverse set of viewpoints.  ...  In particular, we use the factor graph model to obtain features for the argument structure of debates from an online debating platform and incorporate these features to an LSTM-based model to predict the  ...  A.3 BERT Representation Generation We input the utterance in one round for one debater. The segment embedding for each word in the utter-  ... 
arXiv:2010.03538v1 fatcat:yarv2xhcojeevnn5dmsfjrmslu

Historical Document Processing: Historical Document Processing: A Survey of Techniques, Tools, and Trends [article]

James P. Philips, Nasseh Tabrizi
2020 arXiv   pre-print
for further research.  ...  digital format usable in data mining and information retrieval systems.  ...  Techniques for handwriting recognition and optical character recognition alike can be organized into traditional machine learning approaches and deep learning-based approaches using neural networks.  ... 
arXiv:2002.06300v2 fatcat:nxufntuk7famfph6ownyuys2py

Exploring the Role of Argument Structure in Online Debate Persuasion

Jialu Li, Esin Durmus, Claire Cardie
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
Online debate forums provide users a platform to express their opinions on controversial topics while being exposed to opinions from diverse set of viewpoints.  ...  In particular, we use the factor graph model to obtain features for the argument structure of debates from an online debating platform and incorporate these features to an LSTM-based model to predict the  ...  A.3 BERT Representation Generation We input the utterance in one round for one debater. The segment embedding for each word in the utter-  ... 
doi:10.18653/v1/2020.emnlp-main.716 fatcat:yohqhw3z4vdrzomooq23hl6fga

Book of Abstracts of the Digital Humanities in the Nordic Countries 5th conference. Riga, 20–23 October 2020 [article]

Sanita Reinsone, Anda Baklāne, Jānis Daugavietis
2020 Zenodo  
Acknowledgements We thank the Fritz Thyssen Foundation for their funding for the research project Distant Viewing.  ...  We thank the Staatsbibliothek Berlin for providing access to the Wegehaupt collection.  ...  Short paper presentations Topics: data mining / text mining, speech processing, political science, artificial intelligence Keywords: automatic speaker identification, elections, deep neural networks  ... 
doi:10.5281/zenodo.4107117 fatcat:6ongky6p5rab7gvtawnjmp2ofm

Certified Robustness to Adversarial Word Substitutions [article]

Robin Jia and Aditi Raghunathan and Kerem Göksel and Percy Liang
2019 arXiv   pre-print
This paper considers one exponentially large family of label-preserving transformations, in which every word in the input can be replaced with a similar word.  ...  A.R. is supported by a Google PhD Fellowship and the Open Philanthropy Project AI Fellowship.  ...  We thank Allen Nie for providing the pre-trained language model, and thank Peng Qi, Urvashi Khandelwal, Shiori Sagawa, and the anonymous reviewers for their helpful comments.  ... 
arXiv:1909.00986v1 fatcat:4svzb673p5fpdldoclimxd336u

Proceedings of the 5th International Conference on Live Interfaces

Øyvind Brandtsegg, Daniel Formo
2020 Zenodo  
The use of a selection of off-the-shelf and well known synthesizers could be enlightening in comparing this mapping approach with other alternatives.  ...  The artists/engineeers involved in the case studies are: Andi Otto, Frank Baldé (for the STEIM software and Michel A natural immediate prospect will be the exploration of a variety of input devices and  ...  Regarding the modular approach to interfaces, there is also a question of the scope of the interface.  ... 
doi:10.5281/zenodo.3928018 fatcat:z2yfhor2pngmxawzlzgl22y2fq

Chairs: INTELLI Steering Committee INTELLI 2017 Committee INTELLI Steering Committee Program Committee Members

Leo Van Moergestel, Gil Goncalves, Sungshin Kim, Lars Braubach, Hochschule Bremen, Germany Leo Van Moergestel, Maiga Chang, Stefano Berretti, David Greenhalgh, Carsten Behn, Paolo Spagnolo, Gil Gonçalves (+102 others)
unpublished
We are grateful to the members of the INTELLI 2017 organizing committee for their help in handling the logistics and for their work to make this professional meeting a success.  ...  We hope that INTELLI 2017 was a successful international forum for the exchange of ideas and results between academia and industry and for the promotion of progress in the field of intelligent systems  ...  ACKNOWLEDGMENT The authors would like to thank Ş imal Ş en, Sinan Kahraman, Deniz Sezen Gezmiş for annotations and feedbacks about chat bot and Nihan Karslıoglu for her support to improve the system.  ... 
fatcat:h5jggzqlc5eadkuq7nzpvtpgte