[ 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 [2011/11/30 15:08]
popel
courses:rg [2016/10/06 08:54]
popel
Line 1: Line 1:
 ~~NOTOC~~ ~~NOTOC~~
-===== 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. For inspiration see the [[courses:rg:wishlist|wishlist]]. Requirements for getting credits: presenting one paper, writing a report about another presented paper, and active participation in the discussions (which is conditioned by reading the papers in advance and attending the meetings). 
  
-^ Contact      | popel at ufal.mff.cuni.cz | +===== Reading Group =====   
-^ Mailing list | rg at ufal.mff.cuni.cz     | +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:  
-List Archive | [[http://ufal.mff.cuni.cz/mailman/listinfo/rg]] | +  * presenting one paper, 
-Meetings     Mondays 15:10room S1 +    * Select a term (write your name to the schedule below) before October 13. 
-Past meetings| [[courses::rg::past|courses::rg::past]] |+    * 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. 
 +    * 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. 
 + 
 +  * 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 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. 
 + 
 +^ Contact      | popel@ufal.mff.cuni.cz | 
 +^ Mailing list | rg@ufal.mff.cuni.cz     | 
 +Meetings     | Tuesdays 15:40, 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 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 |  | | 
 + 
 + 
  
-=== Autumn&Winter 2011/2012 === 
-^ date | **speaker** | **paper** | 
-^ Oct 3 | | startup meeting| 
-^ Oct 10 | | discussion about [[http://ufal.mff.cuni.cz/download/monday_joakim_nivre_woods.pdf|Joakim Nivre's talk]] If you haven't heard about transition-based parsing (MALT parser) read e.g. [[http://stp.ling.uu.se/~nivre/docs/GoTAL3.pdf|one of Nivre's presentations]] | 
-^ Oct 17 | Martin Popel  | Stephen Tratz, Eduard Hovy: [[http://www.aclweb.org/anthology-new/D/D11/D11-1116.pdf|A Fast, Accurate, Non-Projective, Semantically-Enriched Parser]], EMNLP 2011, report by Michal Novák | 
-^ Oct 24 | Martin Majliš | Valentin Spitkovsky, Hiyan Alshawi, Daniel Jurafsky: [[http://www.aclweb.org/anthology/N/N10/N10-1116.pdf|From Baby Steps to Leapfrog: How “Less is More” in Unsupervised Dependency Parsing]], HLT/NAACL 2010, [[courses:rg:From-Baby Steps-to-Leapfrog-How-Less-is-More-in-Unsupervised-Dependency-Parsing:majlis|MM notes]], [[courses:rg:2011-report-baby-steps|report Oldřich Krůza]]| 
-^ Oct 31 | Michal Novák | Dipanjan Das, Slav Petrov: [[http://www.petrovi.de/data/acl11.pdf|Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections]], ACL 2011, [[courses:rg:unsupervised_pos_tagging|report by Marie Konárová]] | 
-^ Nov 7 | Oldřich Krůza | Oldřich Krůza and Vladislav Kuboň: [[http://commondatastorage.googleapis.com/sixtease/junk/a2clauses.pdf|Automatic Extraction of Clause Relationships from a Treebank]], CICLing 2009, report by Petr Jankovský | 
-^ Nov 14 | Marie Konárová | Majid Yazdani and Andrei Popescu-Belis: [[http://www.aclweb.org/anthology-new/W/W11/W11-1105.pdf|Using a Wikipedia-based Semantic Relatedness Measure for Document Clustering]], TextGraphs Workshop 2011, report by [[courses:rg:Using a Wikipedia-based Semantic Relatedness Measure for Document Clustering|Martin Majliš]] | 
-^ Nov 21 | Petr Jankovský | 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, report by Petra Galuščáková | 
-^ Nov 28 | Jindřich Libovický | Philipp Koehn, Jean Senellart: [[http://homepages.inf.ed.ac.uk/pkoehn/publications/tm-smt-amta2010.pdf|Convergence of Translation Memory and Statistical Machine Translation]], AMTA 2010 | 
-^ Dec 5 | Tomáš Kraut | Sujith Ravi and Kevin Knight: [[http://aclweb.org/anthology/P/P11/P11-1002.pdf | Deciphering Foreign Language]], ACL 2011 | 
-^ Dec 12 | Petra Galuščáková | Maja Popović, Aljoscha Burchardt: [[http://www.mt-archive.info/EAMT-2011-Popovic.pdf| From Human to Automatic Error Classification for Machine Translation Output]], EAMT 2011 | 
-^ Dec 19 | no RG | there is no RG this week (because of UFAL Xmas seminar) | 
-^ Jan 9  | ? | ? | 

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