Differences

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

--- papers:tr-bottou-2011 [2015/12/10 14:46]
leonb
+++ papers:tr-bottou-2011 [2016/09/12 09:44] (current)
leonb [Notes]
@@ Line 27: / Line 27: @@
 A revision of this text was published in [[bottou-mlj-2013| 2014 (MLJ)]].
+===== Notes =====
+This documents cite the work of Vincent Etter (2009) carried out during his NEC Labs internship. Vincent's master report is now available on [[http://vincent.etter.io/publications/etter2009master.pdf|his home page]] ({{vincentetter.pdf|local copy}}). Section 5 is an exploration of that were extensively discussed between Ronan Collobert, Jason Weston and I. We had the hope to discover relevant recursive sentence representation in an unsupervised manner. Alas, we found that the shape of the structure of a recursive network has very little impact on its representation abilities, something that was clearly confirmed by [[https://arxiv.org/pdf/1301.2811.pdf|Scheible and Schütze (2013)]] on a sentiment classification task. Even a left-to-right tree (which amounts to using a recurrent neural network in fact) works essentially as well, something that was cleanly confirmed by [[http://arxiv.org/pdf/1506.01057v1.pdf|Li et al. (2015)]] on a broad collection of NLP tasks.  I still had hopes to make it work when I wrote this tech report in 2010. However these two works have convinced me that structure discovery won't happen without a new idea.