GitHub - ptakopysk/lemata

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 124 Commits
papers		papers
run		run
run10k		run10k
scores		scores
shc		shc
10k_hom		10k_hom
LICENSE		LICENSE
README		README
add_tags.py		add_tags.py
add_tags.shc		add_tags.shc
add_tags_50l.shc		add_tags_50l.shc
add_tags_50l_all.shc		add_tags_50l_all.shc
add_tags_PARAMS.shc		add_tags_PARAMS.shc
add_tags_PARAMS_cos.shc		add_tags_PARAMS_cos.shc
add_tags_PARAMS_jw.shc		add_tags_PARAMS_jw.shc
analthresh_lc_50l_ROOT_SIM.shc		analthresh_lc_50l_ROOT_SIM.shc
analyze_lc_50l_ROOT_SIM_PARAMS.shc		analyze_lc_50l_ROOT_SIM_PARAMS.shc
analyze_pairs.py		analyze_pairs.py
analyze_pairs.shc		analyze_pairs.shc
analyze_pairs_new.py		analyze_pairs_new.py
analyze_pairs_new.shc		analyze_pairs_new.shc
analyze_root_fomrs.py		analyze_root_fomrs.py
base_1k.shc		base_1k.shc
bup_m10k		bup_m10k
check.py		check.py
clean_lemma_forms.py		clean_lemma_forms.py
clean_lemma_forms.shc		clean_lemma_forms.shc
clean_lemma_forms.shca		clean_lemma_forms.shca
clust_lc_50l_ROOT_SIM.shc		clust_lc_50l_ROOT_SIM.shc
clustep_lc_50l_ROOT_SIM.shc		clustep_lc_50l_ROOT_SIM.shc
clustepb_lc_50l_ROOT_SIM.shc		clustepb_lc_50l_ROOT_SIM.shc
cluster.py		cluster.py
cluster_baselines.sh		cluster_baselines.sh
cluster_baselines_100k.sh		cluster_baselines_100k.sh
cluster_merges.sh		cluster_merges.sh
cluster_test.py		cluster_test.py
cluster_test.sh		cluster_test.sh
cluster_test.txt		cluster_test.txt
cluster_test_100k.sh		cluster_test_100k.sh
cluster_test_100k.shc		cluster_test_100k.shc
cluster_test_10k.sh		cluster_test_10k.sh
cluster_test_10k.shc		cluster_test_10k.shc
cluster_test_10k.txt		cluster_test_10k.txt
cluster_test_1M.shc		cluster_test_1M.shc
cluster_test_1M_jcl.shc		cluster_test_1M_jcl.shc
cluster_test_sm.sh		cluster_test_sm.sh
conll2simpletagger.py		conll2simpletagger.py
conll2simpletagger.shc		conll2simpletagger.shc
conll2simpletagger_50l.shc		conll2simpletagger_50l.shc
cs_pdt-ud-dev.conllu		cs_pdt-ud-dev.conllu
cs_pdt-ud-test.conllu		cs_pdt-ud-test.conllu
cs_pdt-ud-train.conllu		cs_pdt-ud-train.conllu
czech_stemmer.py		czech_stemmer.py
derembs.py		derembs.py
derinet_edges.py		derinet_edges.py
derinet_neighbours.py		derinet_neighbours.py
deriv_infl.py		deriv_infl.py
eval.py		eval.py
eval_product.py		eval_product.py
filter_large_roots.py		filter_large_roots.py
filter_neighbours.py		filter_neighbours.py
filter_tags.py		filter_tags.py
filter_tags_agg.py		filter_tags_agg.py
filter_tags_only.py		filter_tags_only.py
forms-new.txt		forms-new.txt
forms2vectors.shc		forms2vectors.shc
int.shc		int.shc
int_1k_lc.shc		int_1k_lc.shc
int_50l_lc.shc		int_50l_lc.shc
intersect_cnk_derinet.py		intersect_cnk_derinet.py
intersect_vectors.py		intersect_vectors.py
intersect_vectors_lc.py		intersect_vectors_lc.py
lemma_finder.py		lemma_finder.py
lemma_finder_agg.py		lemma_finder_agg.py
lemma_form_lists.py		lemma_form_lists.py
lemma_form_lists.shca		lemma_form_lists.shca
lemma_forms.py		lemma_forms.py
lemma_forms.shc		lemma_forms.shc
lemmas_in_pdt.py		lemmas_in_pdt.py
neighbour_pairs.py		neighbour_pairs.py
neighbour_pairs_dertype.py		neighbour_pairs_dertype.py
neighbour_pairs_dertype2.py		neighbour_pairs_dertype2.py
neighbour_pairs_dertype_lc.py		neighbour_pairs_dertype_lc.py
neighbour_pairs_new.py		neighbour_pairs_new.py
neighbour_pairs_new.shc		neighbour_pairs_new.shc
plot_bars.py		plot_bars.py
plot_bars_cutoff.py		plot_bars_cutoff.py
plot_cdf.py		plot_cdf.py
plot_cdf_weighted.py		plot_cdf_weighted.py
plot_lc_1k.shc		plot_lc_1k.shc
plot_lc_1k_cos.shc		plot_lc_1k_cos.shc
plot_lc_1k_jw.shc		plot_lc_1k_jw.shc
plot_lc_50l_ROOT_SIM.shc		plot_lc_50l_ROOT_SIM.shc
prfplot_lc_50l_ROOT_SIM.shc		prfplot_lc_50l_ROOT_SIM.shc
run_50l_top50roots_all3sims.sh		run_50l_top50roots_all3sims.sh
run_clust_50l_top50roots_best_output.sh		run_clust_50l_top50roots_best_output.sh
run_clust_50l_top50roots_best_output_test.sh		run_clust_50l_top50roots_best_output_test.sh
sm		sm
snv_log		snv_log
stem_neighbours.py		stem_neighbours.py

Repository files navigation

Lemmatization across languages

Code used for experiments for the following two papers:

- Unsupervised Lemmatization as Embeddings-Based Word Clustering
https://arxiv.org/abs/1908.08528

- Attempting to separate inflection and derivation using vector space representations
https://www.aclweb.org/anthology/W19-8508/

The main code file is cluster.py