Both sides previous revision
Previous revision
Next revision
|
Previous revision
Next revision
Both sides next revision
|
courses:rg [2007/04/03 16:10] pecina |
courses:rg [2015/11/16 12:31] popel |
~~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: |
| * presenting one paper, |
| * 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 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. |
| |
^ Contact | pecina at ufal.mff.cuni.cz | | * active participation in the discussions, which is conditioned by reading the papers in advance and attending the meetings, |
^ Meetings | Wednesdays 9:30 | | * 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. |
| |
=== Program === | 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 | Mondays 16:00, 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]] | |
| |
=== Summer 2005/2006 === | === Autumn&Winter 2015/2016 (preliminary plan) === |
| ^ date | **speaker** | **paper** | |
^ 1. 3. | Ondřej Bojar | David Chiang (2005): A Hierarchical Phrase-Based Model for Statistical Machine Translation In proceedings of ACL'05. USA, Michigan, Ann Arbor. || | ^ Oct 5 | | startup meeting | |
^ 8.3. | Zdeněk Žabokrtský | Sylvain Kahan: The Meaning-Text Theory || | ^ 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]] | |
^ 15.3. | Pavel Schlesinger | Noah A. Smith and Jason Eisner (2005): Contrastive Estimation: Training Log-Linear Models on Unlabeled Data. In Proceedings of the Association for Computational Linguistics (ACL 2005), Ann Arbor, Michigan || | ^ 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]] | |
^ 22.3. | Pavel Pecina | Deepak Ravichandran; Patrick Pantel; Eduard Hovy (2005) Randomized Algorithms and NLP: Using Locality Sensitive Hash Functions for High Speed Noun Clustering, ACL, Ann Arbor || | ^ Oct 26 | Lukáš, Milan | hands-on tutorial on using some neural network toolkit | |
^ 29.3. | All | diskuse nad budocnosti RG || | ^ 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]] | |
^ 5.4. | Pavel Stranak | Keh-Jiann Chen, Chi-Ching Luo, Ming-Chung Chang, Feng-Yi Chen, Chao-Jan Chen, Chu-Ren Huang: Sinica Treebank: Design criteria, representational issues and implementation || | ^ Nov 9 | — | no RG, dean's day | |
^ 12.4. | Zdenek Zabokrtsky | Sgall, Petr (1995). "Prague School Typology". In: Masayoshi Shibatani and Theodora Bynon (eds), Approaches to Language Typology. Clarendon Press, Oxford United Kingdom. || | ^ Nov 16 | | cont. from last RG | |
^ 19.4. | Bara Hladka | B. Scholkopf, A.J. Smola: A Short Introduction to Learning Method with Kernels. || | ^ Nov 23 | Milan, Lukáš | NN hackaton | |
^ 26.4. | | || | ^ 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]]| |
^ 3.5. | Ota Smrz | || | ^ Dec 7 | | hackaton | |
^ 10.5. | Bara Hladka | B. Scholkopf, A.J. Smola: A Short Introduction to Learning Method with Kernels. | cont'd | | ^ 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]] | |
| |
=== Winter 2005/2006 === | |
| |
^ Oct 19 | Kiril Ribarov | **Non-projective Dependency Parsing using Spanning Tree Algorithms** | | |
^ Oct 26 | Petr Podveský | K. Crammer and Y. Singer: **Ultraconservative on-line algorithms for multiclass problems**, JMLR, 2003 | | |
^ Nov 2 | Jiří Havelka | L. Georgiadis: **Arborescence optimization problems solvable by Edmonds’ algorithm**. | | |
^ Nov 9 | Barbora Hladká | | | |
^ Nov 16 | Pavel Pecina | B. Moore: **Discriminative Framework for Bilingual Word Alignment**, EMNLP, Vancouver, 2005 | | |
^ Nov 23 | Ota Smrž | Noah A. Smith, David A. Smith, Roy W. Tromble: **Context-Based Morphological Disambiguation with Random Fields** || | |
^ Nov 30 | Václav Novák | J. Eisner and D. Karakos: **Bootstrapping Without the Boot**, HLT/EMNLP, Vancouver, 2005 | | |
^ Dec 7 | Pavel Schlesinger| B. Taskar, D. Klein, M. Collins, D. Koller and C. Manning: **Max-Margin Parsing**, EMNLP, Barcelona, 2004. | | |
^ Dec 14 | Daniel Zeman | D. Zeman, Z. Zabokrstky: **Improving Parsing Accuracy by Combining Diverse Dependecy Parsers**, IWPT, Vancouver, 2005 | | |
^ Jan 4 | Ondřej Bojar | Franz Och: **Tutorial**, MT Summit, 2005. | | |
^ Jan 11 | Jiří Semecký | M. Carpuat and D. Wu: **Word Sense Disambiguation vs. Statistical Machine Translation**. | | |
| |