Differences

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

--- resources [2015/12/18 00:08]
kmh
+++ resources [2015/12/18 00:10]
kmh
@@ Line 16: / Line 16: @@
 ===== Combinatory Categorial Autoencoders =====
-The code for my 2013 ACL paper on compositional semantics using CCG and vectors is hosted on Github: [[https://github.com/karlmoritz/oxcvsm]]
+The code for my 2013 ACL paper on compositional semantics using CCG and vectors is hosted on Github: [[https://github.com/karlmoritz/oxcvsm]]. Note that this code is deprecated and I suggest you look at the BiCVM package (below) instead, which supersedes this package and should provide a cleaner, more easily extensible model.
-This is a new (cleaner) implementation compared to the one used for the paper, and I haven't migrated all models to the new version yet. This will be updated this over time and I will also add documentation.
 ===== Multilingual Models for Compositional Semantics =====
-The code for my 2014 ACL and ICLR papers on learning multilingual word embeddings and language models is hosted on Github: [[https://github.com/karlmoritz/bicvm]]. A cleaner version of this code is in the making and will be published at some point. However, the current version suffices for replicating the results in my papers and can easily be extended with more complex composition functions.
+The code for my 2014 ACL and ICLR papers on learning multilingual word embeddings and language models is hosted on Github: [[https://github.com/karlmoritz/bicvm]]. The code in BiCVM works for replicating the results in my papers and can easily be extended with more complex composition functions.
 As part of these publications I have published a modified version of the TED corpus ([[https://wit3.fbk.eu/]]), which you can find
 [[http://www.clg.ox.ac.uk/tedcorpus|here]].