[CaCL] glove paper

[Michael White]

It turns out that Yoav Goldberg has a blog post and writeup saying that
glove's performance is quite similar to word2vec in an apples-to-apples
comparison:

https://plus.google.com/114479713299850783539/posts/BYvhAbgG8T2

On Wed, Oct 15, 2014 at 10:52 AM, Marten van Schijndel <
van-schijndel.1 at buckeyemail.osu.edu> wrote:

> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> GloVe
> http://www-nlp.stanford.edu/projects/glove/glove.pdf
>
> Abstract: Recent methods for learning vector space representations of
> words have succeeded in capturing fine-grained semantic and syntactic
> regularities using vector arithmetic, but the origin of these
> regularities has remained opaque. We analyze and make explicit the
> model properties needed for such regularities to emerge in word
> vectors. The result is a new global log-bilinear regression model that
> combines the advantages of the two major model families in the
> literature: global matrix factorization and local context window
> methods. Our model efficiently leverages statistical information by
> training only on the nonzero elements in a word-word co-occurrence
> matrix, rather than on the entire sparse matrix or on individual
> context windows in a large corpus. The model produces a vector space
> with meaningful substructure, as evidenced by its performance of 75%
> on a recent word analogy task. It also outperforms related models on
> similarity tasks and named entity recognition.
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1
>
> iQIcBAEBAgAGBQJUPoomAAoJEGlPBEtlZwvAsckQAK9RlUXU2F7JIjcsCMWrexHp
> 4qRqtM/3IF5cxmwy/oQKCqrhs98k2TUtsk5QhYSK1cFi22Uc3CsuwPzxiLxX+mNi
> /4aM4ETCLvp/qNjqx/WgG3qZ4zJsyOCSVIC7jh2fptG/Oc2i/n/SJKbcsQ3jG5ap
> 3qdRzlaAA1cUrN6f1+v7flTMvS7DG4N1rbDpqbehy7MP2rvKowMT4fwR0jSSbFWO
> Xz0FX6egyT+Yklt8jdtPW74Odewy1WSAC455lkvzi5SDffBcneH0vx9V+mO2ct2a
> dRx4jdLJoGQ2Q903QkdpXjR8+okbjYHYALEKWRsjhRzfCtOXTKlUo7segYpp267u
> mxVUO4XacW9oo2yO8yQBHYrOl5M8wlvVBOhwy24gBc/EZrw7LtjnyL3GVNHtY+aB
> 1WrKUC96qqLHIhuYFPy05/5K3+Cr/7AXE0ENP+JphbQr35iDVGBmOLEXNlbBx+6b
> zSSs3+/4xR88vhZVgQfTQopDJLJqYK1xRqNdRu12/Pd2prpHCv5TQ0Yyt7vELigi
> NZOLWVNtm7BmibTgFJ1UHUcN0nx+UntLNNgWv8RsRXwUMXSZX30nNPYHPKpfAdHW
> 2888b2rp21Ciu8aWjs9dgq+k5FrsPQcSlYzGAmgML6Z/U9Y4mTeCjTCUZPeIoFHH
> YyeydxDbbOhos0dlFXaj
> =FnSx
> -----END PGP SIGNATURE-----
>
> _______________________________________________
> CaCL mailing list
> CaCL at mail.ling.ohio-state.edu
> http://mail.ling.ohio-state.edu/cgi-bin/mailman/listinfo/cacl
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osu.edu/pipermail/cacl/attachments/20141112/3a91122e/attachment.html>