[ 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 [2014/09/19 17:17]
ufal +small ad for our new RG
courses:rg [2014/12/30 10:10]
popel
Line 3: Line 3:
 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 February 24+    * 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 3. 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--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.     * 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 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 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.
Line 16: Line 16:
 ^ 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     |
-^ Meetings     | Mondays 15:45, room S1 |+^ Meetings     | Mondays 16:00, room 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]] | ^ Other reading groups  | [[https://github.com/ufal/rg/wiki|Machine Learning RG]] |
-=== Spring&Summer 2014 === 
-^ date   | **speaker** | **paper** | 
-^ Feb 24 |             | startup meeting, John Langford: [[http://hunch.net/?p=224|All Models of Learning have Flaws]], 2007 | 
-^ Mar  3 | Vincent     | RExtractor – A Framework for Extracting Relations from Texts, 2014 | 
-^ Mar 10 | Rudolf      | MLFix | 
-^ Mar 17 | Petra       | paraphrases | 
-^ Mar 23 | Martin      | [[http://ufal.mff.cuni.cz/~popel/treex/sheet.pdf|Treex]]  | 
-^ Mar 31 | Ivana       | Sun, Grishman, Sekine: [[http://aclweb.org/anthology/P/P11/P11-1053.pdf|Semi-supervised Relation Extraction with Large-scale Word Clustering]], ACL 2011 | 
-^ Apr  7 | Loganathan  | McDonald, Petrov, Hall: [[http://www.aclweb.org/anthology/D11-1006.pdf|Multi-source Transfer of Delexicalized Dependency Parsers]], EMNLP 2011 | 
-^ Apr 14 | Vincent     | Keith Hall: [[http://aclweb.org/anthology-new/P/P07/P07-1050.pdf|k-best Spanning Tree Parsing]], ACL 2007 | 
-^ <del>Apr 21</del> | no RG       | Easter | 
-^ Apr 28 | Rudolf      | Goldberg, Elhadad: [[http://www.aclweb.org/anthology/N10-1115.pdf|An Efficient Algorithm for Easy-First Non-Directional Dependency Parsing]], NAACL 2010 | 
-^ May  5 | Petra  | Goldberg, Orwant: [[http://www.aclweb.org/anthology/S13-1035.pdf|A Dataset of Syntactic-Ngrams over Time from a Very Large Corpus of English Books]], 2013 | 
-^ May 12 | Ivana  | short paper for LAW VIII | 
-^ May 19 | Ruda, Petra | dry-run presentations for LREC | 
  
 +=== Autumn&Winter 2014/2015 ===
 +^ date   | **speaker**  | **paper** |
 +^ Oct  6 |              | startup meeting |
 +^ Oct 13 | Jindřich Libovický | Peter F. Brown et all.: [[http://www.aclweb.org/anthology/J92-4003|Class-Based n-gram Models of Natural Language]], Computational Linguistics, 1992. See also [[http://statmt.blogspot.cz/2014/07/understanding-mkcls.html| notes about the mkcls implementation]] |
 +^ Oct 20 | Tomáš Kraut | 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]]|
 +^ Oct 27  | Roman Sudarikov | 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]]|
 +^ Nov 3 | Dušan Variš | 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 10 | Duc Tam Hoang | Joseph Turian, Lev Ratinov, Yoshua Bengio: [[http://anthology.aclweb.org//P/P10/P10-1040.pdf|Word representations: A simple and general method for semi-supervised learning]], ACL 2010. [[courses:rg:2014:wr|Questions]]|
 +^ <del>Nov 17</del> | --- | no RG (Struggle for Freedom and Democracy Day) |
 +^ Nov 24 | Vendula Michlíková | 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]] |
 +^ Dec 1  | Richard Ejem | Marco Pennacchiotti, Patrick Pantel: [[http://www.aclweb.org/anthology/D09-1025|Entity Extraction via Ensemble Semantics]], ACL 2009. [[courses:rg:2014:entity|Questions]] |
 +^ Dec 8  | Nguyen Tien Dat| Elia Bruni,... and Marco Baroni: [[http://www.aclweb.org/anthology/W11-2503.pdf|Distributional semantics from text and images]], EMNLP 2011 : [[http://www.aclweb.org/anthology/P12-1015.pdf|Distributional Semantics in Technicolor]], ACL 2012 [[courses:rg:2014:mDSM|Questions]]|
 +^ Dec 15 |Ahmad Aghaebrahimian |Qingqing Cai, Alexander Yates: [[http://knight.cis.temple.edu/~yates/papers/open-sem-parsing.pdf|Semantic Parsing Freebase: Towards Open-domain Semantic Parsing]] SEM,2013 [[courses:rg:2014:start|Questions]]|
 +^ Jan 5  | Michal Auersperger | Mark Johnson: [[http://cs.brown.edu/courses/cs195-5/fall2009/docs/lecture_10-27.pdf|A brief introduction to kernel classifiers]] [[courses:rg:2014:kernels|Questions]] |

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