Closed Moustafa-Banbouk closed 10 years ago
As you can probably see, UD is very much a work in progress at the moment!
At the moment, CoreNLP comes with a Stanford Dependencies version for English and Chinese only. These have been recently updated to include some UD relations and ideas, but not the most major changes (such as the change from preposition as head to nmod
).
More recently we have started work on two fronts: (i) A new shift-reduce dependency parser by @danqi, and (ii) support for converting Penn Treebank-style constituency trees to UD. Within the coming months, we hope to have both of these supporting UD, but it's going to take some time.
Thanks a lot professor for the fast reply,
Wish you all the best in your future progress and by the way I was one of the first who had the owner of joining your NLP course on Coursera. It was really successful and the amount of positive impact on NLP practitioners was huge.
It will also be great if we can build a discussion forum for discussing modern NLP issues.
Best regards, Moustafa Banbouk
On Wed, Oct 8, 2014 at 6:27 AM, Christopher Manning < notifications@github.com> wrote:
As you can probably see, UD is very much a work in progress at the moment!
At the moment, CoreNLP comes with a Stanford Dependencies version for English and Chinese only. These have been recently updated to include some UD relations and ideas, but not the most major changes (such as the change from preposition as head to nmod).
More recently we have started work on two fronts: (i) A new shift-reduce dependency parser by @danqi https://github.com/danqi, and (ii) support for converting Penn Treebank-style constituency trees to UD. Within the coming months, we hope to have both of these supporting UD, but it's going to take some time.
— Reply to this email directly or view it on GitHub https://github.com/UniversalDependencies/docs/issues/92#issuecomment-58297220 .
Hi there,
I am planning to develop an application based on Stanford's CoreNLP engine and would like to know how can I use Universal Dependencies in Java-Based CoreNLP.
Thanks in advance,