From 6ead7d0e4e8de97d23c13989b3968cab873a0342 Mon Sep 17 00:00:00 2001 From: Paul Baltescu Date: Thu, 2 Oct 2014 11:59:05 +0100 Subject: Fix time tracking for suffix array construction. --- extractor/sacompile.cc | 1 + 1 file changed, 1 insertion(+) (limited to 'extractor') diff --git a/extractor/sacompile.cc b/extractor/sacompile.cc index 3ee668ce..d80ab64d 100644 --- a/extractor/sacompile.cc +++ b/extractor/sacompile.cc @@ -114,6 +114,7 @@ int main(int argc, char** argv) { stop_write = Clock::now(); write_duration += GetDuration(start_write, stop_write); + stop_time = Clock::now(); cerr << "Constructing suffix array took " << GetDuration(start_time, stop_time) << " seconds" << endl; -- cgit v1.2.3 From d3560fafafb8e1e907d44c7b544f15eee22c8245 Mon Sep 17 00:00:00 2001 From: Paul Baltescu Date: Thu, 2 Oct 2014 12:56:15 +0100 Subject: Update C++ extractor ReadMe. --- extractor/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'extractor') diff --git a/extractor/README.md b/extractor/README.md index 642fbd1d..11138007 100644 --- a/extractor/README.md +++ b/extractor/README.md @@ -1,4 +1,4 @@ -C++ implementation of the online grammar extractor originally developed by [Adam Lopez](http://www.cs.jhu.edu/~alopez/). +A simple and fast C++ implementation of a SCFG grammar extractor using suffix arrays. The implementation is described in this [paper](https://ufal.mff.cuni.cz/pbml/102/art-baltescu-blunsom.pdf). The original cython extractor is described in [Adam Lopez](http://www.cs.jhu.edu/~alopez/)'s PhD [thesis](http://www.cs.jhu.edu/~alopez/papers/adam.lopez.dissertation.pdf). The grammar extraction takes place in two steps: (a) precomputing a number of data structures and (b) actually extracting the grammars. All the flags below have the same meaning as in the cython implementation. -- cgit v1.2.3 From 8601c7fa4ca6fe8093ec54cd2c150cf130484297 Mon Sep 17 00:00:00 2001 From: Paul Baltescu Date: Thu, 2 Oct 2014 15:52:24 +0100 Subject: Correct binary name in extractor ReadMe. --- extractor/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'extractor') diff --git a/extractor/README.md b/extractor/README.md index 11138007..b83ff900 100644 --- a/extractor/README.md +++ b/extractor/README.md @@ -4,7 +4,7 @@ The grammar extraction takes place in two steps: (a) precomputing a number of da To compile the data structures you need to run: - cdec/extractor/compile -a -b -c -o + cdec/extractor/sacompile -a -b -c -o To extract the grammars you need to run: -- cgit v1.2.3