CS707 Data and Web Science Seminar (FSS 2016)
The Data and Web Science seminar covers recent topics in data and web science. This term, the seminar focuses on neural networks for text analytics.
GoalsIn this seminar, you will
- Read, understand, and explore scientific literature
- Summarize a current research topic in a concise report
- Give two presentations about your topic (one 3 minutes, one 15 minutes)
- Moderate a scientific discussion about a topic of one of your fellow students
- Provide feedback to a report and to a presentation of a fellow student
- Select your preferred topics and register by February 17 (see below)
- Attend the kickoff meeting (date/location to be disclosed) [slides: pdf]
- You will be assigned an advisor, who provides guidance and one-to-one meetings
- Work individually throughout the semester: explore literature, write a report, peer-review, create and give two presentations
- Full schedule [pdf]
Explore the list of topics below and select at least 3 topics of your preference. Send a ranked list of your selected topics via email to k.gashteovski(at)uni-mannheim(dot)de until February 17, 2016. We will confirm your registration immediately. The actual topic assignment takes place soon after the registration deadline and we will notify you via e-mail. Our goal is, of course, to assign to you to one of your preferred topics.
The papers and articles listed below serve as an entry point to a topic; you are expected to explore related relevant literature on your own.
- Machine Reading
Hermann, Karl Moritz, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. "Teaching machines to read and comprehend." In Advances in Neural Information Processing Systems, pp. 1684-1692. 2015.
Chen, Danqi, and Christopher D. Manning. "A fast and accurate dependency parser using neural networks." Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Vol. 1. 2014.
- Question Answering
Iyyer, Mohit, et al. "A neural network for factoid question answering over paragraphs." Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014
- Word representation
Luong, Minh-Thang, Richard Socher, and Christopher D. Manning. "Better word representations with recursive neural networks for morphology." CoNLL-2013 104 (2013)
Mikolov, Tomas, et al. "Distributed representations of words and phrases and their compositionality." Advances in neural information processing systems. 2013.
- Text classification
Johnson, Rie, and Tong Zhang. "Effective use of word order for text categorization with convolutional neural networks." North American Chapter of the Association for Computational Linguistics – Human Language Technologies, 2015 (NAACL HLT 2015)
Zhang, Xiang, Junbo Zhao, and Yann LeCun. "Character-level convolutional networks for text classification." Advances in Neural Information Processing Systems. 2015
- Relation classification
Zeng, Daojian, Kang Liu, Siwei Lai, Guangyou Zhou and Jun Zhao. "Relation classification via convolutional deep neural network." Proceedings of COLING. 2014.
dos Santos, Cıcero Nogueira, Bing Xiang, and Bowen Zhou. "Classifying relations by ranking with convolutional neural networks." Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Vol. 1. 2015.
- Machine translation
Hu, Yuening, et al. "Minimum translation modeling with recurrent neural networks." Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics. 2014
- Opinion mining
Irsoy, Ozan, and Claire Cardie. "Opinion mining with deep recurrent neural networks." Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing
Students are free to suggest alternative topics.
If you are new to neural networks, these resources may help to get you started:
- A Deep Learning Tutorial: From Perceptrons to Deep Networks
- Free e-book: Neural Network and Deep Learning
- Stanford Deep Learning Tutorial
- Blog: http://colah.github.io/
Additional resources about neural network for text analytics include:
- Deep Learning in Natural Language Processing (by Stanford)
- Tutorial: Deep Learning for Natural Language Processing (without Magic)
- Course: Deep Learning for Natural Learning Processing (by Stanford, with materials)
In case you need some NLP background, checkout these MOOCs:
- Natural Language Processing (by Stanford, instructors: Christopher Manning and Dan Jurafsky)
- Natural Language Processing (by Columbia University, instructor: Michael Collins)
- Introduction to Natural Language Processing (by University of Michigan, instructor: Dragomir R. Radev)
Giving talks / writing reports:
- "Giving conference talks", by Prof. Dr. Rainer Gemulla [pdf]
- "Writing for Computer Science" by Justin Zobel