(c) Mark Johnson,Eugene Charniak, 24th November 2005 --- August 2006
We request acknowledgement in any publications that make use of this
software and any code derived from this software. Please report the
release date of the software that you are using (this is part of the
name of the tar file you have downloaded), as this will enable others
to compare their results to yours.
NEW!!! The first stage parser, which uses about 95% of the time, is
now multi-treaded. The default is two threads. Currently the maximum
is four. To change the number (or maximum) see the README file for
the first-stage parser. For the time being a non-threaded version is
available in case there are problems with threads. Send email to ec
if you have problems. See below for details.
COMPILING THE PARSER
To compile the two-stage parser, first define GCCFLAGS appropriately
for your machine, e.g., with csh or tcsh
> setenv GCCFLAGS "-march=pentium4 -mfpmath=sse -msse2 -mmmx"
> setenv GCCFLAGS "-march=opteron -m64"
(if unsure, it is safe to leave GCCFLAGS unset -- it just won't be
as optimized as possible)
After it has built, the parser can be run with
> parse.sh <sourcefile.txt>
> parse.sh sample-text/sample-data.txt
The script parse-eval.sh takes a list of treebank files as arguments
and extracts the terminal strings from them, runs the two-stage parser
on those terminal strings and then evaluates the parsing accuracy with
the U. Penn EVAL-B program. For example, on my machine the Penn
Treebank 3 CD-ROM is installed at /usr/local/data/Penn3/, so the
following code evaluates the two-stage parser on section 24.
> parse-eval.sh /usr/local/data/Penn3/parsed/mrg/wsj/24/wsj*.mrg
USING THE PARSER
See first-stage/README for more information.
TRAINING THE RERANKER
Retraining the reranker takes a considerable amount of time, disk
space and RAM. At Brown we use a dual Opteron machine with 16Gb RAM,
and it takes around two days. You should be able to do it with only
8Gb RAM, and maybe even with 4Gb RAM with an appropriately tweaked
kernel (e.g., sysctl overcommit_memory, and a so-called 4Gb/4Gb split
if you're using a 32-bit OS).
The time and memory you need depend on the features that the reranker
extracts and the size of the n-best tree training and development
data. You can change the features that are extracted by changing
second-stage/programs/features/features.h, and you can reduce the size
of the n-best tree data by reducing NPARSES in the Makefile from 50
to, say, 25.
You will need to edit the Makefile in order to retrain the reranker.
First, you need to set the variable PENNWSJTREEBANK in Makefile to the
directory that holds your version of the Penn WSJ Treebank. On my
machine this is:
You'll also need the Boost C++ and the Petsc/Tao C++ libraries in
order to retrain the reranker. The environment variables PETSC_DIR
and TAO_DIR should all point to the installation directories of this
software. I define these variables in my .login file as follows on my
setenv PETSC_DIR /usr/local/share/petsc
setenv TAO_DIR /usr/local/share/tao
setenv PETSC_ARCH linux
setenv BOPT O_c++
While many modern Linux distributions come with the Boost C++
libraries pre-installed, if the Boost C++ libraries are not included
in your standard libraries and headers, you will need to install them
and add an include file specification for them in your GCCFLAGS. For
example, if you have installed the Boost C++ libraries in
/home/mj/C++/boost, then your GCCFLAGS environment variable should be
> setenv GCCFLAGS "-march=pentium4 -mfpmath=sse -msse2 -mmmx -I /home/mj/C++/boost"
> setenv GCCFLAGS "-march=opteron -m64 -I /home/mj/C++/boost"
Once this is set up, you retrain the reranker as follows:
> make reranker
> make nbesttrain
> make eval-reranker
The script train-eval-reranker.sh does all of this.
The reranker goal builds all of the programs, nbesttrain constructs
the 20 folds of n-best parses required for training, and eval-reranker
extracts features, estimates their weights and evaluates the
reranker's performance on the development data (dev) and the two test
data sets (test1 and test2).
If you have a parallel processor, you can run 2 (or more) jobs
in parallel by running
> make -j 2 nbesttrain
Currently this only helps for nbesttrain (but this is the slowest
step, so maybe this is not so bad).
The Makefile contains a number of variables that control how the
training process works. The most important of these is the VERSION
variable. You should do all of your experiments with VERSION=nonfinal,
and only run with VERSION=final once to produce results for publication.
If VERSION is nonfinal then the reranker trains on WSJ PTB sections
2-19, sections 20-21 are used for development, section 22 is used as
test1 and section 24 is used as test2 (this approximately replicates
the Collins 2000 setup).
If VERSION is final then the reranker trains on WSJ PTB sections 2-21,
section 24 is used for development, section 22 is used as test1 and
section 23 is used as test2.
The Makefile also contains variables you may want to change, such as
NBEST, which specfies how many parses per sentence are extracted from
each sentence, and NFOLDS, which specifies how many folds are created.
If you decide to experiment with new features or new feature weight
estimators, take a close look at the Makefile. If you change the
features please also change FEATURESNICKNAME; this way your new
features won't over-write our existing ones. Similarly, if you change
the feature weight estimator please pick a new ESTIMATORNICKNAME and
if you change the n-best parser please pick a new NBESTPARSERNICKNAME;
this way you new n-best parses or feature weights won't over-write the
To get rid of (many of) the object files produced in compilation, run:
> make clean
Training, especially constructing the 20 folds of n-best parses,
produces a lot of temporary files which you can remove if you want to.
To remove the temporary files used to construct the 20 fold n-best
> make nbesttrain-clean
All of the information needed by the reranker is in
second-stage/models. To remove everything except the information
needed for running the reranking parser, run:
> make train-clean
To clean up everything, including the data needed for running the
reranking parser, run:
> make real-clean
To use the non-threaded parser instead change the following line
in the Makefile
It should now read:
That is, it is identical except for the "o" in oparseIt
Then run oparse.sh, rather than parse.sh.
INSTALLING PETSC AND TAO
You'll need to have PETSc and Tao installed in order to
retrain the reranker.
These installation instructions work for gcc version 4.2.1 (you also
need g++ and gfortran).
1. Unpack PETSc and TAO somewhere, and make shell variables point
to those directories (put the shell variable definitions in your
.bash_profile or equivalent)
ln -s petsc-2.3.3-p6 petsc
ln -s tao-1.9 tao
2. Configure and build PETSc
FLAGS="-march=native -mfpmath=sse -msse2 -mmmx -O3 -ffast-math"
./config/configure.py --with-cc=gcc --with-fc=gfortran --with-cxx=g++ --download-f-blas-lapack=1 --with-mpi=0 --with-clanguage=C++ --with-shared=1 --with-dynamic=1 --with-debugging=0 --with-x=0 --with-x11=0 COPTFLAGS=$FLAGS FOPTFLAGS=$FLAGS CXXOPTFLAGS=$FLAGS
3. Configure and build TAO