aboutsummaryrefslogtreecommitdiffstats
path: root/README.md
diff options
context:
space:
mode:
authorYigit Sever2019-09-27 22:04:33 +0300
committerYigit Sever2019-09-27 22:04:33 +0300
commit35d2af6a15ec2070dd3c28e5d28212c42770b7fe (patch)
treeaef66d80727e9a4441b01d0eebe50cfbf253d85e /README.md
parent97848102702d1914fa208f06916ea597faa5ce24 (diff)
downloadEvaluating-Dictionary-Alignment-35d2af6a15ec2070dd3c28e5d28212c42770b7fe.tar.gz
Evaluating-Dictionary-Alignment-35d2af6a15ec2070dd3c28e5d28212c42770b7fe.tar.bz2
Evaluating-Dictionary-Alignment-35d2af6a15ec2070dd3c28e5d28212c42770b7fe.zip
Include batch scripts
Diffstat (limited to 'README.md')
-rw-r--r--README.md17
1 files changed, 14 insertions, 3 deletions
diff --git a/README.md b/README.md
index e80d946..ff2256d 100644
--- a/README.md
+++ b/README.md
@@ -157,7 +157,10 @@ Example;
157python WMD.py en bg bilingual_embeddings/en_to_bg.vec bilingual_embeddings/bg_to_en.vec wordnets/ready/en_to_bg.def wordnets/ready/bg_to_en.def wmd retrieval 157python WMD.py en bg bilingual_embeddings/en_to_bg.vec bilingual_embeddings/bg_to_en.vec wordnets/ready/en_to_bg.def wordnets/ready/bg_to_en.def wmd retrieval
158``` 158```
159 159
160Will run on English and Bulgarian definitions, using WMD for retrieval. 160Will run on English and Bulgarian definitions, using WMD for retrieval. We included a batch script to run WMD and SNK with retrieval and matching on all available language pairs;
161```
162./run_wmd.sh
163```
161 164
162### sentence_embedding.py - Sentence Embedding Representation 165### sentence_embedding.py - Sentence Embedding Representation
163 166
@@ -193,7 +196,11 @@ Example;
193python sentence_embedding.py it ro bilingual_embeddings/it_to_ro.vec bilingual_embeddings/ro_to_it.vec wordnets/ready/it_to_ro.def wordnets/ready/ro_to_it.def matching 196python sentence_embedding.py it ro bilingual_embeddings/it_to_ro.vec bilingual_embeddings/ro_to_it.vec wordnets/ready/it_to_ro.def wordnets/ready/ro_to_it.def matching
194``` 197```
195 198
196Will run on Italian and Romanian definitions, using sentence embedding representation for matching. 199Will run on Italian and Romanian definitions, using sentence embedding representation for matching. We included a batch script to run alignment using sentence embeddings using retrieval and matching on all available language pairs;
200
201```
202./run_semb.sh
203```
197 204
198 205
199### learn_and_predict.py - Supervised Alignment 206### learn_and_predict.py - Supervised Alignment
@@ -234,4 +241,8 @@ Example;
234python learn_and_predict.py -sl en -tl ro -df ./wordnets/tsv_files/en_to_ro.tsv -es bilingual_embeddings/en_to_ro.vec -et bilingual_embeddings/ro_to_en.vec 241python learn_and_predict.py -sl en -tl ro -df ./wordnets/tsv_files/en_to_ro.tsv -es bilingual_embeddings/en_to_ro.vec -et bilingual_embeddings/ro_to_en.vec
235``` 242```
236 243
237Will run on English and Romanian definitions. 244Will run on English and Romanian definitions. We included a batch script to run supervised alignment on all available pairs;
245
246```
247./run_supervised.sh
248```