| Both sides previous revision
Previous revision
Next revision
|
Previous revision
Next revision
Both sides next revision
|
courses:rg [2013/03/04 21:09]
kosao7am questions |
courses:rg [2016/06/06 17:18]
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: | 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--6 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 ([[http://ufal.mff.cuni.cz/mailman/listinfo/rg|subscribe]] first) by Monday 16:00. | * 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 23:59 (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. |
| ^ 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 | Mondays 17:20, S6 | |
| ^ 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]] | |
| |
| === Spring&Summer 2013 === | === Spring&Summer 2016 === |
| ^ date | **speaker** | **paper** | | ^ date | **speaker** | **paper** | |
| ^ Feb 18 | | startup meeting| | ^ Feb 22 | Martin Popel | W Ammar, G Mulcaire, M Ballesteros, C Dyer, NA Smith: [[http://arxiv.org/pdf/1602.01595.pdf|One Parser, Many Languages]] 2016 | |
| ^ 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]] | | ^ Feb 29 | | cont. | |
| ^ Mar 4 | Ondřej Dušek | Michael Collins, Nigel Duffy: [[http://www.cs.cmu.edu/Groups/NIPS/NIPS2001/papers/psgz/AA58.ps.gz|Convolution kernels for natural language]], NIPS 2001. [[courses:rg:2013:convolution-kernels|Questions]] | | ^ Mar 7 | Jindřich Libovický | Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, Wojciech Zaremba: [[http://arxiv.org/abs/1511.06732|Sequence Level Training with Recurrent Neural Networks]], 2016 | |
| ^ Mar 11 | Ondřej Košarko | Aron Culotta, Jeffrey Sorensen: [[http://www.newdesign.aclweb.org/anthology-new/P/P04/P04-1054.pdf|Dependency Tree Kernels for Relation Extraction]], ACL 2004. [[courses:rg:2013:dep-tree-kernels|Questions]] | | ^ Mar 14 | Jindřich Libovický | cont. | |
| ^ Mar 18 |Jindřich Helcl | Intro to Structured prediction. 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. As for the intro, [[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 more]]). | | ^ May 21 | Jindřich Helcl | Debanjan Ghosh, Weiwei Guo, Smaranda Muresan: [[http://www.aclweb.org/anthology/D15-1116|Sarcastic or Not: Word Embeddings to Predict the Literal or Sarcastic Meaning of Words]] EMNLP 2015 | |
| ^ Mar 25 | Sara van de Moosdijk | 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]] | | ^ Mar 28 | no RG | Easter Monday | |
| ^ Apr 1 |--- | no RG, Easter (and April Fool's Day) | | ^ Apr 4 | Milan Straka | Stack LSTM http://arxiv.org/abs/1505.08075 | |
| ^ Apr 8 | Vincent Kríž | John Lafferty, Andrew McCallum, Fernando Pereira: [[http://www.cis.upenn.edu/~pereira/papers/crf.pdf|Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data]], 2001 | | ^ Apr 11 | Milan Straka | [[http://arxiv.org/abs/1603.06270|Multi-Task Cross-Lingual Sequence Tagging from Scratch]] and eventually also [[http://arxiv.org/abs/1603.01360|Network Architectures for NER]] | |
| ^ Apr 15 | Ondřej Fiala | Ashish Venugopal, Jakob Uszkoreit, David Talbot, Franz J. Och, Juri Ganitkevitch: [[http://aclweb.org/anthology-new/D/D11/D11-1126.pdf|Watermarking the Outputs of Structured Prediction with an application in Statistical Machine Translation]], 2011 | | ^ Apr 18 | Rudolf Rosa | Rico Sennrich, Barry Haddow, Alexandra Birch: [[http://arxiv.org/pdf/1508.07909v3.pdf|Neural Machine Translation of Rare Words with Subword Units]], 2016| |
| ^ Apr 22 | Matěj Korvas | Yansong Feng, Mirella Lapata: [[http://aclweb.org/anthology-new/N/N10/N10-1125.pdf|Topic Models for Image Annotation and Text Illustration]] | | ^ Apr 25 | Tom Kocmi | Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan: [[https://arxiv.org/abs/1603.06155|A Persona-Based Neural Conversation Model]], 2016| |
| ^ Apr 29 | Karel Bílek | | | ^ May 2 | Pasky | Petr Baudiš, Jan Šedivý: [[http://pasky.or.cz/sps.pdf|Sentence Pair Scoring: Towards Unified Framework for Text Comprehension]], 2016 | |
| ^ May 6 | Jan Mašek | | | ^ May 9 | Martin Popel | Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu, Hang Li: [[https://arxiv.org/pdf/1601.04811v3.pdf|Modeling Coverage for Neural Machine Translation]], 2016 | |
| ^ May 13 | Matouš Macháček | | | ^ May 16 | Shadi Saleh | Guido Zuccon et al. [[http://dl.acm.org/citation.cfm?id=2838936|Integrating and evaluating neural word embeddings in information retrieval]], 2015 | |
| ^ May 20 | Petr Jankovský | last RG | | ^ May 23 | special last RG | travelling to LREC | |
| |
