Differences

This shows you the differences between two versions of the page.

--- courses:rg [2012/10/16 18:25]
korvas Budu prezentovat Berkeley aligner -- MK
+++ courses:rg [2015/11/28 21:25]
popel
@@ Line 1: / Line 1: @@
 ~~NOTOC~~
-===== Reading Group =====
+===== Reading Group =====
 Official name of this course is [[https://is.cuni.cz/studium/predmety/index.php?do=predmet&kod=NPFL095|NPFL095]] **Modern Methods in Computational Linguistics**. It is a continuation of informal Reading Group (RG) meetings. Requirements for getting credits:
   * presenting one paper,
-    * Select a term (write your name to the schedule below) before Oct 8.
+    * Select a term (write your name to the schedule below) before October 13.
-    * Suggest [[mailto:popel@ufal.mff.cuni.cz|me]] 2--3 papers you would like to present (with pdf links, and your preferences) before Oct 15.
+    * If no paper is assigned to the term, suggest [[mailto:popel@ufal.mff.cuni.cz|me]] 2--3 papers you would like to present (with pdf links, and your preferences) before October 20. Ideally, make a group of 2--4 students presenting papers on a common topic (starting from basics to more advance papers).
-    * Prepare your presentation and three quiz questions.
+    * Prepare your presentation and 3--5 quiz questions. At least 3 of the questions should ask for a specific answer, e.g. "write an equation for...", "given training set X=([dog,N],[cat,Y]), what is the number..." (Not "what do you think about..."). The first question should be quite easy to answer for those who have read the whole paper. The last question may be a tricky one. Send me the questions two weeks before your presentation. We may discuss the paper and refine the questions.
-    * One week ahead of the presentation, remind it to rg@ufal.mff.cuni.cz ([[http://ufal.mff.cuni.cz/mailman/listinfo/rg|subscribe]] first), you may add details and the quiz questions.
+    * One week before the presentation, write the questions to a dedicated wiki page here. Send a reminder (questions and a link to the pdf of the paper) to rg@ufal.mff.cuni.cz by Monday 15:45.
-  * writing a report about another presented paper (within one week deadline),
+  * active participation in the discussions, which is conditioned by reading the papers in advance and attending the meetings,
-  * active participation in the discussions, which is conditioned by reading the papers in advance and attending the meetings.
+  * sending your answers to me and the presenter by Saturday 23:59 (so the presenter can go through all answers before the presentation and focus more on problematic parts).
-  * In case of more than three missed meetings or deadlines, additional reports are required.
+  * In case of more than three missed meetings or deadlines, additional work (e.g. reports or answers to tricky questions) will be required.
-All reports and presented papers must be in English. The presentations are in English by default, but if all present people agree it may be in Czech.
+All questions, reports and presented papers must be in English. The presentations are in English by default, but if all present people agree it may be in Czech.
 ^ Contact      | popel@ufal.mff.cuni.cz |
 ^ Mailing list | rg@ufal.mff.cuni.cz     |
-^ List Archive | [[http://ufal.mff.cuni.cz/mailman/listinfo/rg]] |
+^ Meetings     | Mondays 16:00, S1 |
-^ Meetings     | Mondays 16:15, room S1 |
 ^ Past meetings| [[courses:rg:past|courses:rg:past]] |
 ^ Inspiration  | [[courses:rg:wishlist|courses:rg:wishlist]] |
+^ Other reading groups  | [[https://github.com/ufal/rg/wiki|Machine Learning RG]] |
-=== Autumn&Winter 2012/2013 ===
+=== Autumn&Winter 2015/2016 (preliminary plan) ===
-^ date   | **speaker** | **paper** |
+^ date   | **speaker**               | **paper** |
-^ Oct  1 |             | startup meeting|
+^ Oct  5 |              | startup meeting |
-^ Oct  8 | Rudolf Rosa | Hanna Béchara, Yanjun Ma, Josef van Genabith: [[http://mt-archive.info/MTS-2011-Bechara.pdf|Statistical Post-Editing for a Statistical MT System]], MT Summit 2011, [[courses:rg:2012:spe-for-smt|report by Jindra Helcl]] |
+^ Oct 12 | Lukáš, Milan | Programming hackaton, based on [[http://web.stanford.edu/class/cs168/|The Modern Algorithmic Toolbox]], read in advance lecture [[http://web.stanford.edu/class/cs168/l/l1.pdf|1]] and [[http://web.stanford.edu/class/cs168/l/l2.pdf|2]] |
-^ Oct 15 | Ales Tamchyna | Ferhan Ture, Douglas W. Oard and Philip Resnik: [[http://aclweb.org/anthology-new/N/N12/N12-1046.pdf|Encouraging Consistent Translation Choices ]], NAACL 2012, [[courses:rg:2012:encouraging-consistent-translation|report by Ondřej Dušek]] |
+^ Oct 19 | Martin       | Mark Johnson: [[http://cs.brown.edu/courses/cs195-5/fall2009/docs/lecture_10-27.pdf|A brief introduction to kernel classifiers]], 2009. You can also read [[http://ciml.info/dl/v0_9/ciml-v0_9-ch09.pdf|a chapter from ciml.info]]. [[courses:rg:2014:kernels|Questions]] |
-^ Oct 22 | Jindra Helcl  | Zhongqiang Huang, Martin Cmejrek, Bowen Zhou: [[http://www.aclweb.org/anthology/D10-1014|Soft Syntactic Constraints for Hierarchical Phrase-based Translation Using Latent Syntactic Distributions]], EMNLP 2010: 138-147 |
+^ Oct 26 | Lukáš, Milan | hands-on tutorial on using some neural network toolkit |
-^ Oct 29 | Matěj Korvas  | Percy Liang, Ben Taskar, Dan Klein: [[http://www.seas.upenn.edu/~taskar/pubs/naacl06_aba.pdf|Alignment by Agreement]], HLT-NAACL '06 |
+^ Nov  2 | Adéla        | Michael Collins: [[http://ucrel.lancs.ac.uk/acl/W/W02/W02-1001.pdf|Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms]], EMNLP 2002. [[courses:rg:2014:perceptron|Questions]] |
-^ Nov  5 | Petr Jankovský |  |
+^ Nov  9 | —            | no RG, dean's day |
-^ Nov 12 | Karel Bílek  |  |
+^ Nov 16 |              | cont. from last RG |
-^ Nov 19 | Matous Machacek|  |
+^ Nov 23 | Milan, Lukáš | NN hackaton |
-^ Nov 26 | Ondřej Dušek    | François Mairesse, Milica Gašić, Filip Jurčíček, Simon Keizer, Blaise Thomson, Kai Yu and Steve Young: [[http://newdesign.aclweb.org/anthology/P/P10/P10-1157.pdf|Phrase-based Statistical Language Generation using Graphical Models and Active Learning]], ACL 2010 |
+^ Nov 30 | Aneta        | Andrew McCallum, Dayne Freitag, Fernando Pereira: [[http://www.ai.mit.edu/courses/6.891-nlp/READINGS/maxent.pdf|Maximum Entropy Markov Models for Information Extraction and Segmentation]], Conference on Machine Learning 2000, [[http://courses.ischool.berkeley.edu/i290-dm/s11/SECURE/gidofalvi.pdf|slides]] [[courses:rg:2014:memm|Questions]]|
-^ Dec  3 | Honza Václ |  |
+^ Dec  7 | Adéla        | Charles J. Fillmore: [[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.494.5064&rep=rep1&type=pdf|Border Conflicts: FrameNet Meets Construction Grammar]], 2008  |
-^ Dec 10 | Lukas Zilka |  |
+^ Dec 14 |              | John Lafferty, Andrew McCallum, Fernando Pereira: [[http://www.cs.utah.edu/~piyush/teaching/crf.pdf|Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data]], 2001. [[courses:rg:2014:crf|Questions]] |
-^ Dec 17 | Josef Čech |  |
-^ Jan  7 | | last RG |

[ Back to the navigation ] [ Back to the content ]

Institute of Formal and Applied Linguistics Wiki

Differences