Hi Jian,
That depends on the nature of the features you're planning to
implement.
In order to produce sparse features, you need to write a feature
function anyway.
But if it's only a handful of scores and they can be calculated during
extraction time, then go for dense features and add the
i just compiled on Windows/cygwin ok. Unfortunately, you do need to be
quite experienced with computer science and linux to get very far with
moses.
The company, Precision Translation Tools, have adapted Moses specifically
for Windows (without cygwin).
see the example under 'Comparison With Other Toolkits'
if you have a corpus file called 'text' and you want to create a 5-gram
language model, the command is
lmplz -o 5 --interpolate_unigrams 0 text text.arpa
Hieu Hoang
Researcher
New York University, Abu Dhabi
http://www.hoang.co.uk/hieu
On
Hi,
Are you planning to use binary domain indicator features? I'm not sure
whether a sparse feature function for this is currently implemented. If
you're working with a small set of domains, you can employ dense
indicators instead (domain-features = indicator in EMS). You'll have
to re-extract
Hi Matthias,
Not for domain feature.
I want to implement some sparse features, so there are two options:
1, add to phrase table, if it is supported
2, implement sparse feature functions,
I'd like to know are there any difference between these two options, for
example, tuning, compute sentence
Hi,
I'm experiencing some problems in compiling Moses on Windows using
Cygwin. I manually installed Boost (v. 1.58), but when I run the command
~/mosesdecoder
$ ./bjam --with-boost=~/boost_1_58_0/ -j4
the build fails.
I'm attaching the 'build.log.gz' file, as suggested in the error
Hi
When do we run this command for testing translation input-output
/home/ashok/mosesdecoder-RELEASE-3.0/bin/moses -f
/home/ashok/working/train/model/moses.ini
can some one tell me *where and which variable store input(input from
terminal) and output (translated output ).*
Regards
Ashok Kumar
On 15/07/2015 20:18, Vincent Nguyen wrote:
Hello,
Sorry if this is basic but I am trying to get started and something is
unclear to me in the manual :
Section 2.1.3 recommends (Hieu) Mgiza for Word Alignment and says
Moses includes KenLM
which makes me understand that IRSTLM and SRILM
you need to create a language model. You can do it with kenlm using the
program lmplz. The program is described here:
https://kheafield.com/code/kenlm/estimation/
We haven't updated the tutorial with more info about lmplz yet, but we
should do at some point
I have read this page, but
Hi,
Is the sparse features at phrase table, like
das Haus ||| the house ||| 0.8 0.5 0.8 0.5 2.718 ||| 0-0 1-1 ||| 5000 5000
2500 ||| dom_europarl 1
still supported? If yes, what should I set to the ini file based on the
example above?
Thank,
Jian
--
Jian Zhang
Centre for Next Generation
Hello Manuela,
have you installed all the dependencies listed here for Cygwin
installation? http://www.statmt.org/moses/?n=Development.GetStarted
it seems like you're missing a system-wide installation of boost.
mosesdecoder/bjam currently isn't set-up to use the boost-jam of a local
boost
Hello,
Sorry if this is basic but I am trying to get started and something is
unclear to me in the manual :
Section 2.1.3 recommends (Hieu) Mgiza for Word Alignment and says
Moses includes KenLM
which makes me understand that IRSTLM and SRILM are optional.
Build is fine.
Section
12 matches
Mail list logo