Differences

This shows you the differences between two versions of the page.

--- courses:rg:wishlist [2012/10/08 22:24]
rosa +hmeant (nemam konkrétní článek)
+++ courses:rg:wishlist [2012/10/14 22:07]
popel 4 new suggestions
@@ Line 9: / Line 9: @@
 ==== Machine Learning ====
-  * Something about [[http://searn.hal3.name/|SEARN]] or [[http://www.cs.utah.edu/~hal/megam/|MegaM]] and/or its applications
+  * Something about <del>[[http://searn.hal3.name/|SEARN]]</del>, [[http://www.cs.utah.edu/~hal/megam/|MegaM]], [[http://hunch.net/~vw/|Vowpal Wabbit]] and/or its applications. [[courses:rg:2012:searn-in-practice|SEARN]] could be presented once again, if someone goes through the source codes.
   * 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]]
   * 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
@@ Line 24: / Line 24: @@
   * Phil Blunsom, Trevor Cohn, Chris Dyer and Miles Osborne: [[http://homepages.inf.ed.ac.uk/pblunsom/pubs/blunsom-acl09.pdf|A Gibbs Sampler for Phrasal Synchronous Grammar Induction. ACL-IJCNLP 2009]]
   * Trevor Cohn and Phil Blunsom: [[http://homepages.inf.ed.ac.uk/pblunsom/pubs/cohn-blunsom-emnlp09.pdf|A Bayesian Model of Syntax-Directed Tree to String Grammar Induction. EMNLP 2009.]]
-  * Some MEANT or HMEANT paper, look for Dekai Wu as author or (better) ask Ondřej Bojar
+==== MT Evaluation ====
+  * Martin Popel would appreciate two RG meetings devoted to significance tests & MT evaluation. The two presenters should together read the following 4 papers (and related ones) and select two for presenting (one on bootstrap, one on approximate randomization).
+    - Stefan Riezler and John T. Maxwell III: [[http://acl.ldc.upenn.edu/W/W05/W05-0908.pdf|On Some Pitfalls in Automatic Evaluation and Significance Testing for MT]] (page 67) ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation, 2005.
+    - Nicolas Stroppa, Karolina Owczarzak, Andy Way: [[http://doras.dcu.ie/15227/1/stroppa_owczarzak_07.pdf|A Cluster-Based Representation for Multi-System MT Evaluation]], 2007.
+    - Philipp Koehn: [[http://acl.ldc.upenn.edu/acl2004/emnlp/pdf/Koehn.pdf|Statistical significance tests for machine translation evaluation]], EMNLP 2004.
+    - Ying Zhang, Stephan Vogel, Alex Waibel: [[http://www.lrec-conf.org/proceedings/lrec2004/pdf/755.pdf|Interpreting BLEU/NIST Scores: How Much Improvement Do We Need to Have a Better System?]]
+  * Chi-kiu LO and Dekai WU: [[http://www.cs.ust.hk/~dekai/library/WU_Dekai/LoWu_Acl2011.pdf|MEANT: An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility via semantic frames. ACL HLT 2011]] (or other MEANT or HMEANT paper, but this one seems to be THE main one)
 ==== Other ====

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

Institute of Formal and Applied Linguistics Wiki

Differences