[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki


[ Back to the navigation ]

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
courses:rg [2013/02/18 15:53]
popel
courses:rg [2016/10/06 08:54]
popel
Line 1: Line 1:
 ~~NOTOC~~ ~~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:  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,   * presenting one paper,
-    * Select a term (write your name to the schedule below) before Feb 25+    * Select a term (write your name to the schedule below) before October 13
-    * 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 March 4. Ideally, make a group of 2--4 students presenting papers on a common topic (starting from basics to more advance papers). +    * 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 3--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. +    * Prepare your presentation and 3--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 before the presentation, write the 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 ([[http://ufal.mff.cuni.cz/mailman/listinfo/rg|subscribe]] first). +    * 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.
-    * One week after the presentation (at the latest), write your (or the best) answers below the questions, plus a summary of interesting points discussed at the presentation (report).+
  
   * 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 Friday ??:59 (so the presenter can go through all answers before the presentation and focus more on problematic parts). +  * 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 (or answers to tricky questions) 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 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. 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.
Line 17: Line 17:
 ^ Contact      | popel@ufal.mff.cuni.cz | ^ Contact      | popel@ufal.mff.cuni.cz |
 ^ Mailing list | rg@ufal.mff.cuni.cz     | ^ Mailing list | rg@ufal.mff.cuni.cz     |
-^ List Archive | [[http://ufal.mff.cuni.cz/mailman/listinfo/rg]] | +^ Meetings     Tuesdays 15:40, S1 |
-^ Meetings     Mondays 16:00room S1 |+
 ^ Past meetings| [[courses:rg:past|courses:rg:past]] | ^ Past meetings| [[courses:rg:past|courses:rg:past]] |
 ^ Inspiration  | [[courses:rg:wishlist|courses:rg:wishlist]] | ^ Inspiration  | [[courses:rg:wishlist|courses:rg:wishlist]] |
 +^ Other reading groups  | [[https://github.com/ufal/rg/wiki|Machine Learning RG]] |
 +
 +=== Autumn&Winter 2016/2017 ===
 +^ date   | **speaker**               | **paper** |
 +^ Oct  4 |   | startup meeting |
 +^ Oct 11 | Martin Popel | Kevin Knight, Beáta Megyesi and Christiane Schaefer: [[http://www.isi.edu/natural-language/people/copiale-11.pdf|The Copiale Cipher]], BUCC 2011, you can watch a [[https://www.youtube.com/watch?v=Eam0Tk-1FyI|trailer]] |
 +^ Oct 18 | Daniela Bodanská  | Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu: [[http://aclweb.org/anthology-new/P/P02/P02-1040.pdf|BLEU: a Method for Automatic Evaluation of Machine Translation]], ACL 2002. [[courses:rg:2014:bleu|Questions]] |
 +^ Oct 25 |  | 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 1  |  | 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|Question]]|
 +^ <del>Nov 8</del> | --- | no RG (Dean's day)|
 +^ Nov 15 |  | 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]] |
 +^ Nov 22 |  | Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean: [[http://arxiv.org/pdf/1301.3781.pdf|Efficient Estimation of Word Representations in Vector Space]], ICLR 2013 |
 +^ Nov 29  |  | |
 +^ Dec 6  |  | |
 +^ Dec 13 |  | |
 +
 +
 +
  
-=== Spring&Summer 2013 === 
-^ date   | **speaker** | **paper** | 
-^ Feb 18 |             | startup meeting| 
-^ Feb 25 | Martin Popel| 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_8/ciml-v0_8-ch09.pdf|a chapter from cimpl.info]] | 
-^ Mar 4  |    | Michael Collins, Nigel Duffy: [[http://www.cs.cmu.edu/Groups/NIPS/NIPS2001/papers/psgz/AA58.ps.gz|Convolution kernels for natural language]], NIPS 2001. | 
-^ Mar 11 |    | Aron Culotta, Jeffrey Sorensen: [[http://www.newdesign.aclweb.org/anthology-new/P/P04/P04-1054.pdf|Dependency Tree Kernels for Relation Extraction]], ACL 2004. | 
-^ Mar 18 |    | Intro to Structured prediction. [[http://people.mmci.uni-saarland.de/~titov/teaching/seminar-struct-prediction/struct-pred-class-01.pdf|Ivan Titov]] or [[http://nlpers.blogspot.cz/2006/04/what-is-structured-prediction.html|Hal Daumé]] have nice materials ([[http://nlpers.blogspot.cz/2006/01/structured-prediction-1-whats-out.html|Hal has many]]), but I have not selected any particular yet. | 
-^ Mar 25 |    | 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.| 
-^ Apr 1  |    | no RG, Easter (and April Fool's Day) | 
-^ Apr 8  |    | | 
-^ Apr 15 |    | | 
-^ Apr 22 |    | | 
-^ Apr 1  |    | | 
-^ May 6  |    | | 
-^ May 13 |    | | 
-^ May 20 |    | last RG | 

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