Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Determine whether Factorie provides chunk information #5

Open
schmmd opened this issue Jun 12, 2014 · 3 comments
Open

Determine whether Factorie provides chunk information #5

schmmd opened this issue Jun 12, 2014 · 3 comments
Labels

Comments

@schmmd
Copy link
Member

schmmd commented Jun 12, 2014

Ideally we would stop using OpenNLP. Factorie may provide the chunk information needed. If it provides a constituency parse, this can be reduced to chunks, and likely at higher precision than the OpenNLP chunker.

@kwhumphreys
Copy link
Contributor

The point of chunks is to get some syntactic structure from a fast scan, without the expense of a full constituency parse.
If we're running a constituency parse, why not just use it rather than reducing it?


From: Michael Schmitz
Sent: 6/12/2014 4:39 PM
To: allenai/nlpstack
Subject: [nlpstack] Determine whether Factorie provides chunk information (#5)

Ideally we would stop using OpenNLP. Factorie may provide the chunk information needed. If it provides a constituency parse, this can be reduced to chunks, and likely at higher precision than the OpenNLP chunker.


Reply to this email directly or view it on GitHubhttps://github.com//issues/5.

@schmmd
Copy link
Member Author

schmmd commented Jun 13, 2014

Because we have infrastructure that depends on a chunker. Your point
stands however.

On Thu, Jun 12, 2014 at 4:54 PM, kwhumphreys notifications@github.com
wrote:

The point of chunks is to get some syntactic structure from a fast scan,
without the expense of a full constituency parse.
If we're running a constituency parse, why not just use it rather than
reducing it?


From: Michael Schmitz
Sent: 6/12/2014 4:39 PM
To: allenai/nlpstack
Subject: [nlpstack] Determine whether Factorie provides chunk information
(#5)

Ideally we would stop using OpenNLP. Factorie may provide the chunk
information needed. If it provides a constituency parse, this can be
reduced to chunks, and likely at higher precision than the OpenNLP chunker.


Reply to this email directly or view it on GitHub<
https://github.com/allenai/nlpstack/issues/5>.


Reply to this email directly or view it on GitHub
#5 (comment).

@kwhumphreys
Copy link
Contributor

ok, then perhaps describe it as something like "expose constituents as chunks"?


From: Michael Schmitz
Sent: 6/12/2014 5:09 PM
To: allenai/nlpstack
Cc: Kevin Humphreys
Subject: Re: [nlpstack] Determine whether Factorie provides chunk information (#5)

Because we have infrastructure that depends on a chunker. Your point
stands however.

On Thu, Jun 12, 2014 at 4:54 PM, kwhumphreys notifications@github.com
wrote:

The point of chunks is to get some syntactic structure from a fast scan,
without the expense of a full constituency parse.
If we're running a constituency parse, why not just use it rather than
reducing it?


From: Michael Schmitz
Sent: 6/12/2014 4:39 PM
To: allenai/nlpstack
Subject: [nlpstack] Determine whether Factorie provides chunk information
(#5)

Ideally we would stop using OpenNLP. Factorie may provide the chunk
information needed. If it provides a constituency parse, this can be
reduced to chunks, and likely at higher precision than the OpenNLP chunker.


Reply to this email directly or view it on GitHub<
https://github.com/allenai/nlpstack/issues/5>.


Reply to this email directly or view it on GitHub
#5 (comment).


Reply to this email directly or view it on GitHubhttps://github.com//issues/5#issuecomment-45962966.

@dirkgr dirkgr added the low label Jul 16, 2014
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
Projects
None yet
Development

No branches or pull requests

3 participants