[ 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 [2010/04/21 15:36]
popel Cteni na 26.4.
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. 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.
  
 +  * 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 |  | |
  
  
  
  
- 
- 
- 
- 
- 
- 
- 
- 
- 
- 
- 
- 
- 
- 
- 
- 
-===== Reading Group ===== 
- 
-^ Contact ​     | popel at ufal.mff.cuni.cz | 
-^ Mailing list | rg at ufal.mff.cuni.cz ​    | 
-^ List Archive | [[http://​ufal.mff.cuni.cz/​mailman/​listinfo/​rg]] | 
-^ Meetings ​    | Mondays 15:00, in front of 422 | 
- 
-=== Wishlist === 
- 
- 
-  * Mark Johnson: [[http://​acl.ldc.upenn.edu/​D/​D07/​D07-1031.pdf|Why Doesn'​t EM Find Good HMM POS-Taggers?​]] (Ondřej) 
-  * Eugene Charniak: [[http://​acl.ldc.upenn.edu/​A/​A00/​A00-2018.pdf|A maximum-entropy-inspired parser]] (Zdeněk) 
-  * [[http://​www.aclweb.org/​anthology/​W/​W09/​W09-1114.pdf |Abhishek Arun, Chris Dyer, Barry Haddow, Phil Blunsom, Adam Lopez and Philipp Koehn: Monte Carlo Inference and Maximization for Phrase-based Translation. Conference on Computational Natural Language Learning, 2009. ]] 
-  * [[http://​homepages.inf.ed.ac.uk/​pblunsom/​pubs/​blunsom-acl09.pdf|Phil Blunsom, Trevor Cohn, Chris Dyer and Miles Osborne: A Gibbs Sampler for Phrasal Synchronous Grammar Induction. ACL-IJCNLP 2009]] 
-  * [[http://​homepages.inf.ed.ac.uk/​pblunsom/​pubs/​cohn-blunsom-emnlp09.pdf|Trevor Cohn and Phil Blunsom: A Bayesian Model of Syntax-Directed Tree to String Grammar Induction. EMNLP 2009.]] 
- 
-A source of inspiration:​ [[http://​www.statmt.org/​ued/?​n=Public.WeeklyMeeting|Edinburgh Reading Group]] 
- 
- 
-=== Summer 2010 === 
-^ date | **speaker** | **paper** | 
-^ Apr 26 | Martin Popel | [[http://​citeseerx.ist.psu.edu/​viewdoc/​download?​doi=10.1.1.61.1472&​rep=rep1&​type=pdf|Ronald Rosenfeld: A Maximum Entropy Approach to Adaptive Statistical Language Modeling]] | 
-^ Apr 12 | David Mareček | [[http://​acl.ldc.upenn.edu/​P/​P06/​P06-1033.pdf|Jens Nillson, Joakim Nivre, Johan Hall: Graph Transformations in Data-Driven Dependency Parsing]] | 
-^ Mar 29 | Martin Popel | [[http://​acl.ldc.upenn.edu/​N/​N03/​N03-2002.pdf|Jeff Bilmes and Katrin Kirchhoff: Factored Language Models and Generalized Parallel Backoff]] (plus [[https://​www.ee.washington.edu/​techsite/​papers/​documents/​UWEETR-2008-0004.pdf|tutorial]]) | 
-^ Mar 22 | Zdeněk Žabokrtský | [[http://​www.mitpressjournals.org/​doi/​pdf/​10.1162/​coli.2010.36.1.36103|Deniz Yuret and Mehmet Ali Yatbaz: The Noisy Channel Model for Unsupervised Word Sense Disambiguation,​ Computational Linguistics 2010]] | 
-^ Mar 15 | Ondřej Bojar | [[ 
-http://​www.mt-archive.info/​MTS-2009-Koehn-2.pdf|Philipp Koehn and Barry Haddow: Interactive Assistance to Human Translators using Statistical Machine Translation Methods, MT Summit XII, 2009.]] | 
-^ Mar 8 |  | startup meeting | 
- 
-=== Winter 2009/2010 === 
- 
-^ date | **speaker** | **paper** | **přečíst?​** | 
-^ Dec 14 | Martin Popel | [[http://​nlp.csie.ncnu.edu.tw/​~shin/​acl-ijcnlp2009/​proceedings/​CDROM/​EMNLP/​pdf/​EMNLP042.pdf|Wei Lu, Hwee Tou Ng, Wee Sun Lee: Natural Language Generation with Tree Conditional Random Fields]] | | 
-^ Dec 7 | David Mareček | [[http://​www.aclweb.org/​anthology/​P/​P09/​P09-1040.pdf|Nivre,​ J.: Non-Projective Dependency Parsing in Expected Linear Time. ACL 2009]] | | 
-^ Nov 23, Nov 30 | Jana Straková | [[http://​citeseerx.ist.psu.edu/​viewdoc/​download?​doi=10.1.1.23.9849&​rep=rep1&​type=pdf|John Lafferty, Andrew McCallum and Fernando Pereira: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data]], [[http://​www.inference.phy.cam.ac.uk/​hmw26/​papers/​crf_intro.pdf|Hanna M. Wallach. Conditional Random Fields: An Introduction]] | | 
-^ Nov 9 | Zdeněk Žabokrtský | [[http://​www.aclweb.org/​anthology/​E/​E09/​E09-1018.pdf|Eugene Charniak and Micha Elsner: EM Works for Pronoun Anaphora Resolution. EACL 2009]] ​ | | 
-^ Oct 26, Nov 2 | Ondřej Bojar | [[http://​www.isi.edu/​natural-language/​people/​bayes-with-tears.pdf|Kevin Knight: Bayesian Inference with Tears. September 2009.]]\\ článek byl delší, ale čtivý a přesně takové jsou i [[courses:​rg:​bayes-with-tears|Ondrovy poznámky]] k němu | Ano, i s úkoly | 
-^ Oct 19 | Eda Bejček | [[http://​www.aclweb.org/​anthology/​E/​E09/​E09-1082.pdf|Josh Schroeder, Trevor Cohn, and Philipp Koehn: Word Lattices for Multi-Source Translation. EACL 2009]]\\ přehledné rozdělení metod; dobře, že udělali tolik experimentů,​ škoda některých nepodložených interpretací;​ potřebná znalost Mojžíše; omezili množství trénovacích dat -- chybí test, zda více dat není účinnější než více jazyků; klesá skutečně MAX s množstvím jazyků? (to je divné, neměly by se tedy vážit výsledky jednotlivých systémů (viz věta s "​little benefit",​ 2.1)? A nebo není příčinou spíš než přidání šestého jazyka přidání špatného jazyka (Table 6)? Jak by dopadly testy po dvojicích?​);​ v závěru 2.3 vynechávají reordering s odkazem na diversitu zdrojových jazyků -- to nemusí platit |  Ano  | 
-^ Oct 15 | Pavel Pecina | [[http://​portal.acm.org/​citation.cfm?​id=1401975|Daniel David Walker, Eric K. Ringger: Model-based document clustering with a collapsed gibbs sampler]], [[courses:​rg:​2009-10-15-tabule|Fotky tabule]] | | 
-^ Oct 12 | Pavel Schlesinger | Gibbsův sampling (http://​en.wikipedia.org/​wiki/​Gibbs_sampling)| | 
- 
- 
- 
-=== Summer 2009 === 
- 
-^ date | **speaker** | **paper** | 
-^ May 25 | David Mareček | [[http://​www.lrec-conf.org/​proceedings/​lrec2008/​pdf/​286_paper.pdf|Christian Hanig, Stefan Bordag, Uwe Quasthoff: UnsuParse: Unsupervised Parsing with unsupervised Part of Speech tagging. LREC 2009]] | 
-^ May 11 | Václav Novák | [[http://​newdesign.aclweb.org/​anthology-new/​E/​E09/​E09-1007.pdf|Julien Ah-Pine, Guillaume Jacquet: Clique-Based Clustering for improving Named Entity Recognition systems. EACL 2009]] | 
-^ May 4 | Dan Zeman | [[http://​www.aclweb.org/​anthology/​P/​P08/​P08-1059|Kristina Toutanova, Hisami Suzuki, Achim Ruopp: Applying Morphology Generation Models to Machine Translation. ACL 2008, Columbus, Ohio]] | 
-^ Apr 6 | Zdeněk Žabokrtský | [[http://​pauillac.inria.fr/​~pdenis/​papers/​emnlp08.pdf|Pascal Denis and Jason Baldridge, Specialized models and ranking for coreference resolution]] | 
-^ Mar 30 | Pavel Schlesinger |  | 
-^ Mar 9 | Pavel Pecina |  | 
- 
-=== Winter 2008/2009 === 
- 
-^ date | **speaker** | **paper** | 
-^ Mon Jan 5 | Martin Popel | Thorsten Brants, Ashok C. Popat, Peng Xu, Franz J. Och, Jeffrey Dean: {{courses:​rg:​2007brants-large_language_models_in_mt.pdf|Large Language Models in Machine Translation}},​ 2007 | 
-^ Mon Dec 1 | Jan Ptáček | {{courses:​rg:​goldwater-mcclosky-czech-english-mt-0-33.pdf|Improving Statistical MT through Morphological Analysis}} | 
-^ Mon Nov 24 | Pavel Češka | [[http://​citeseerx.ist.psu.edu/​viewdoc/​download;​jsessionid=656CAA9B55D39BC763A26946D91E7FBD?​doi=10.1.1.61.3358&​rep=rep1&​type=pdf|A TAG-based noisy channel model of speech repairs]] | 
-^ Wed Nov 19 | Ondřej Bojar | [[http://​aclweb.org/​anthology-new/​P/​P08/​P08-1023.pdf|Forest Reranking: Discriminative Parsing with Non-Local Features by Liang Huang]] (see Google Tech Talks), [[http://​aclweb.org/​anthology-new/​P/​P08/​P08-1023.pdf|Forest-Based Translation]] by Haitao Mi and Liang Huang and Qun Liu | 
-^ Mon Nov 10 | Zdeněk Žabokrtský | Katja Filippova and Michael Strube: [[http://​www.eml-research.de/​nlp/​papers/​filippova.emnlp08.pdf|Sentence Fusion via Dependency Graph Compression]],​ 2008 | 
-^ Mon Nov 3 | Jiří Mírovský | Alexander E. Richman and Patrick Schone: Mining Wiki Resources for Multilingual Named Entity Recognition,​ ACL, Columbus, 2008. | 
-^ Wed Oct 20 | Jan Raab | Libin Shen, Giorgio Satta, and Aravind K. Joshi: Guided Learning for Bidirectional Sequence Classification,​ ACL, Prague, 2007. | 
- 
-=== Summer 2008 === 
- 
-^ date | **speaker** | **paper** | 
-^ Mar 17 | Pavel Schlesinger | Aria Haghighi and Dan Klein: //​[[http://​www.eecs.berkeley.edu/​~aria42/​pubs/​acl07-hdp-coref.pdf|Unsupervised Coreference Resolution in a Nonparametric Bayesian Model]]//, ACL, Prague, 2007.   ​| ​ 
-^ Mar 31 | Pavel Schlesinger | //​Unsupervised Coreference Resolution in a Nonparametric Bayesian Model//, 2nd part :-)| 
-^ Apr 28 | Pavel Straňák | Diana McCarthy, Rob Koeling, Julie Weeds and John Carroll: //​{{courses:​unsupervised_acquisition_of_predominant_word_senses.pdf|Unsupervised Acquisition of Predominant Word Senses}}// in Computational Linguistics 33 (4), 2007 | 
- 
-=== Winter 2007/2008 === 
-^ Nov 26 | Markéta ​ Lopatková | Friedrich Otto: {{courses:​rg:​tr-ra-tutorial.ps|Restarting Automata (Notes for a Course)}}, Technical Report, Universitat kassel, 2004. | 
-^ Nov 19 | Dan Zeman | Anil Kumar Singh (अनिल कुमार सिंह),​ Jagadeesh Gorla: {{courses:​rg:​kumar-gorla-identification-of-languages.pdf|Identification of Languages and Encodings in a Multilingual Document}} {{courses:​kumar-gorla-identification-of-languages.zip|Identification of Languages and Encodings in a Multilingual Document}}. In: Proceedings of the 3rd ACL SIGWAC Workshop on Web as Corpus, pp. 95-108. Louvain-la-Neuve,​ Belgium, 2007. | 
-^ Nov 12 | Otakar Smrž | M. Nowak, N. Komarova, P. Niyogi. [[http://​people.cs.uchicago.edu/​~niyogi/​papersps/​NKNnature.pdf|Computational and Evolutionary Aspects of Language]]. Nature, Vol. 417, pp. 611-617, 2002. | 
-^ Nov 5 | Jan Ptáček | Philipp Koehn; Hieu Hoang: **{{courses:​factored-translation-models.pdf|Factored Translation Models}}**, EMNLP & CoNLL, Prague, 2007. | 
-^ Oct 29 | Miroslav Spousta | David Talbot; Miles Osborne Smoothed Bloom Filter Language Models: Tera-Scale LMs on the Cheap http://​www.aclweb.org/​anthology-new/​D/​D07/​D07-1049.pdf | 
-^ Oct 17 | Zdeněk Žabokrtský | **Mary Hearne, John Tinsley, Ventsislav Zhechev, Andy Way (2007)**: Capturing Translational Divergences with a Statistical Tree-to-Tree Aligner {{seminare:​hearneetal_tmi_07.pdf|HearneEtAl_TMI_07.pdf}} | 
- 
-=== Summer 2007 === 
- 
-=== Winter 2006/2007 === 
- 
-^ Nov 15 | | Glöckner, Ingo; Sven Hartrumpf; and Hermann Helbig (2006): Automatic knowledge acquisition by semantic analysis and assimilation of textual information {{:​seminare:​reading-group:​gloeckner.ps|gloeckner.ps - plná verze}} | 
- 
-=== Summer 2006 === 
- 
-^ Mar 1  | Ondřej Bojar | D. Chiang: **A Hierarchical Phrase-Based Model for Statistical Machine Translation**,​ ACL, Ann Arbor, 2005. | 
-^ Mar 8  | Zdeněk&​nbsp;​Žabokrtský | S. Kahan: **The Meaning-Text Theory**. | 
-^ Mar 15 | Pavel&​nbsp;​Schlesinger | N. A. Smith and J. Eisner: **Contrastive Estimation: Training Log-Linear Models on Unlabeled Data**. ACL, Ann Arbor, 2005. | 
-^ Mar&​nbsp;​22 | Pavel Pecina | D. Ravichandran,​ P. Pantel and E.Hovy: **Randomized Algorithms and NLP: Using Locality Sensitive Hash Functions for High Speed Noun Clustering**,​ ACL, Ann Arbor, 2005. | 
-^ Apr 5  | Pavel Straňák | 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**. | 
-^ Apr 12 | Zdeněk Žabokrtský | P. Sgall: **Prague School Typology**. In Masayoshi Shibatani and Theodora Bynon (eds), Approaches to Language Typology. Clarendon Press, ​ Oxford, United Kingdom, 1995. | 
-^ Apr 19 | Barbora Hladká | B. Scholkopf and A.J. Smola: ​ **A Short Introduction to Learning Method with  Kernels**. | 
-^ May 3  | Otakar Smrž | || 
-^ May 10 | Barbora Hladká | B. Scholkopf and A.J. Smola: ​ **A Short Introduction to Learning Method with Kernels**. ​ | 
- 
-=== 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**,​ HLT/EMNLP, Vancouver, 2005. | 
-^ Nov 23 | Otakar Smrž         | Noah A. Smith, David A. Smith, Roy W. Tromble: **Context-Based Morphological Disambiguation with Random Fields**. || 
-^ Nov&​nbsp;​30 | Václav Novák ​    | J. Eisner and D. Karakos: **Bootstrapping Without the Boot**, HLT/EMNLP, Vancouver, 2005. | 
-^ Dec 7  | Pavel&​nbsp;​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**. | 

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