Deep Learning is an interesting new branch of machine learning where neural networks consisting of multiple layers have shown new generalization capabilities. The seminar will look at advances in both general deep learning approaches, and at the specific case of Neural Machine Translation (NMT). NMT is a new paradigm in data-driven machine translation. In Neural Machine Translation, the entire translation process is posed as an end-to-end supervised classification problem, where the training data is pairs of sentences and the full sequence to sequence task is handled in one model.
Here is a link to last semester's seminar.
There is a Munich interest group for Deep Learning, which has an associated mailing list (initially organized by David Kaumanns), the paper announcements are sent out on this list. See the link here: http://www.cis.uni-muenchen.de/~davidk/deep-munich/
Email Address: SubstituteLastName@cis.uni-muenchen.de
CIS, LMU Munich
CIS, LMU Munich
Thursdays 14:30 (s.t.), location is room CIS Meeting Room (C105).
Click here for directions to CIS.
New attendees are welcome. Read the paper and bring a paper or electronic copy with you, you will need to refer to it during the discussion.
If this page appears to be out of date, use the refresh button of your browser
|Thursday, October 12th||Philipp Koehn and Rebecca Knowles. Six Challenges for Neural Machine Translation. Workshop on Neural Machine Translation 2017.||paper||Alex Fraser|
|Thursday, October 19th||Recent conference papers||no paper||Ben Roth|
|Thursday, October 26th||Long Duong, Hiroshi Kanayama, Tengfei Ma, Steven Bird, Trevor Cohn (2016). Learning Crosslingual Word Embeddings without Bilingual Corpora. EMNLP||paper||Fabienne Braune|
|Thursday, November 9th||Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Shirui Pan, Chengqi Zhang (2017). DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding. arXiv.||paper||Dario Stojanovski|
|Thursday, November 16th||Rajarshi Das, Manzil Zaheer, Siva Reddy, Andrew McCallum (2017). Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks (2017). ACL.||paper||Ben Roth|
|Thursday, November 23rd||Guillaume Lample, Ludovic Denoyer, Marc'Aurelio Ranzato (2017). Unsupervised Machine Translation Using Monolingual Corpora Only. arXiv.||paper||Helmut Schmid|
|Thursday, November 30th||Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou (2017). Word Translation Without Parallel Data. arXiv.||paper||Sebastian Wagner|
|Thursday, December 7th||Zhaopeng Tu, Yang Liu, Shuming Shi, Tong Zhang (2018). Learning to Remember Translation History with a Continuous Cache. TACL.||paper||Matthias Huck|
|Thursday, January 11th||Sara Sabour, Nicholas Frosst, Geoffrey Hinton (2017). Dynamic Routing Between Capsules. NIPS.||paper||Ben Roth|
|Thursday, January 18th||James Bradbury, Stephen Merity, Caiming Xiong, Richard Socher. Quasi-Recurrent Neural Networks. ICLR 2017||paper (arxiv is outdated)||Dario Stojanovski|
Please click here for an NMT reading list, but also see the more general RNN reading list here (scroll down). You can also go back through the previous semesters by clicking on the link near the top of the page.