BERT Gloss Methods

114.2 - review notebook - multidataset.ipynb

@@ -0,0 +1,111 @@
+{
+ "metadata": {
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.5-final"
+  },
+  "orig_nbformat": 2,
+  "kernelspec": {
+   "name": "python3",
+   "display_name": "Python 3",
+   "language": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2,
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tasks.wsd_gloss import create_md_training_data, train_gloss_and_context"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lemma, pos = 'machine','NN'\n",
+    "senses = {'machine_nn01-38474140'} # machine_nn01-38475772 machine_nn01-38475923 machine_nn01-38475835 machine_nn01-38474140\n",
+    "relations = ['seed','synonym'] # ,'descendant','sibling'\n",
+    "eval_mode = \"lemma_etal\" # lemma or lemma_etal\n",
+    "experiment_id = 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "# senses before filtering by date = 517\n",
+      "# senses after filtering by date = 433\n",
+      "\n",
+      "\n",
+      "# of seed senses 26 \n",
+      "# of synonyms 383 \n",
+      "# of branch senses 0\n",
+      "\n",
+      "\n",
+      "# of seeds selected 1 \n",
+      "# of synonyms selected 44 \n",
+      "# of branches selected 0\n",
+      "[LOG] #rows before removing None vector (1947, 21)\n",
+      "[LOG] #rows after removing None vector (1911, 21)\n"
+     ]
+    }
+   ],
+   "source": [
+    "create_md_training_data(lemma,pos,senses,relations,experiment_id=experiment_id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_gloss_and_context(lemma,pos,experiment_id=experiment_id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ]
+}

run_glossbert.py

@@ -0,0 +1,10 @@
+from tasks.wsd_gloss import create_glossbert_data, train_glossbert
+import sys
+
+def run(lemma,pos):
+    data_path = create_glossbert_data(lemma,pos)
+    train_glossbert(data_path,downsample=True)
+
+if __name__=="__main__":
+    lemma,pos = sys.argv[1],sys.argv[2]
+    run(lemma,pos)

tasks/wsd.py

@@ -106,7 +106,7 @@ def svm_wemb_baseline(df_train,df_test,wemb_model):
     return y_pred
 
 ### ---------------------------------------------------
-# BERT CENTROID METHODS
+#  BERT CENTROID METHODS
 
 ### ---------------------------------------------------
 # binary centroid vectors