| commit | 46cad40f3b2e3abb180faffee5f2d05d327497e3 | [log] [tgz] |
|---|---|---|
| author | Marc Kupietz <kupietz@ids-mannheim.de> | Sun Aug 02 07:23:05 2026 +0200 |
| committer | Marc Kupietz <kupietz@ids-mannheim.de> | Sun Aug 02 07:23:05 2026 +0200 |
| tree | 1f35c4a0a79218e9fbacadb45c666537a881e5f9 | |
| parent | f2aa92e2f798db186af046bcb836fea49b7670f1 [diff] |
Install dereko2vec and vecs2mmap There were no install rules at all, so "make install" stopped with "No rule to make target 'install'", although the README has been telling people to run it. Only the two programs that are useful outside of a build directory are installed. The others keep the generic names they inherited from word2vec, like distance or kmeans_txt, which have no business in a directory on everybody's PATH. The README asked for collocatordb 1.3.0 and ctest3; it now names the rocksdb package of the distribution, collocatordb 1.5.0, which builds against it, and says that the build directory has to be build/ inside the sources, because the test looks for the binary relative to it. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Change-Id: I8637f7faa0b8061e7e016637f5348bc26c9e3529
Fork of wang2vec with extensions for re-training and count based models, support for tokens with frequencies > 2³² and a more accurate ETA prognosis.
librocksdb-dev on Debian and Ubuntu or rocksdb-devel on Fedora and Rocky Linuxcd dereko2vec mkdir build cd build cmake .. make && ctest --extra-verbose && sudo make install
This installs dereko2vec and vecs2mmap. The build directory has to be build inside the sources, the test looks for the binary relative to it.
A completely static dereko2vec is about 10% faster on the collocator database and needs a static rocksdb and a static collocatordb:
cmake -DSTATIC_DEREKO2VEC=ON ..
Debian and Ubuntu ship librocksdb.a in librocksdb-dev. Fedora, Rocky Linux and RHEL do not, the collocatordb README says how to build one there without shadowing the headers of the package.
The command to build word embeddings is exactly the same as in the original version, except that we added type 5 for setting up a purely count based collocation database.
The -type argument is a integer that defines the architecture to use. These are the possible parameters:
0 - cbow
1 - skipngram
2 - cwindow (see below)
3 - structured skipngram(see below)
4 - collobert's senna context window model (still experimental)
5 - build a collocation count database instead of word embeddings
./dereko2vec -train input_file -output embedding_file -type 0 -size 50 -window 5 -negative 10 -nce 0 -hs 0 -sample 1e-4 -threads 1 -binary 1 -iter 5 -cap 0
The KorAP-XML-CoNLL-U tool can be used to generate input files for dereko2vec from KorAP-XML ZIPs using its tokenization and setence boundary information, for example:
korapxml2conllu --word2vec wpd19.zip > wpd19.w2vinput
dereko2vec -train new.traindata -output new.vecs -save-net new.net -type 3 -size 200 -window 5 -negative 10 -threads 44 -binary 1 -iter 100 -read-vocab old.vocab -read-net old.net
dereko2vec -train new.traindata -output new.rocksdb -type 5 -window 5 -threads 8 -binary 1 -iter 1 -read-vocab old.vocab -sample 0 -min-count 0 dereko2vec -train new.traindata -output .temp.rocksdb -type 5 -window 5 -threads 8 -binary 1 -iter 1 -save-vocab new_focus.vocab -sample 0 -min-count 0 rm -rf .temp.rocksdb python scripts/merge_vocabs.py old.vocab new_focus.vocab new.vocab
@InProceedings{Ling:2015:naacl, author = {Ling, Wang and Dyer, Chris and Black, Alan and Trancoso, Isabel}, title="Two/Too Simple Adaptations of word2vec for Syntax Problems", booktitle="Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies", year="2015", publisher="Association for Computational Linguistics", location="Denver, Colorado", } @InProceedings{FankhauserKupietz2019, author = {Peter Fankhauser and Marc Kupietz}, title = {Analyzing domain specific word embeddings for a large corpus of contemporary German}, series = {Proceedings of the 10th International Corpus Linguistics Conference}, publisher = {University of Cardiff}, address = {Cardiff}, year = {2019}, note = {\url{https://doi.org/10.14618/ids-pub-9117}} }