neural bigrams

2023-04-27 11:33:12 +02:00 · 2023-04-27 11:33:12 +02:00 · 9285bffcec
parent c6c596193a
commit 9285bffcec
3 changed files with 17935 additions and 17935 deletions
--- a/cw7zad1.ipynb
+++ b/cw7zad1.ipynb
@ -82,8 +82,8 @@
   "source": [
    "def get_words_from_line(line):\n",
    "    line = clean_line(line)\n",
-    "    for m in re.finditer(r'[\\p{L}0-9\\*]+|\\p{P}+', line):\n",
-    "        yield m.group(0).lower()"
+    "    for word in line.split():\n",
+    "        yield word"
   ],
   "metadata": {
    "collapsed": false
--- a/dev-0/out.tsv
+++ b/dev-0/out.tsv
--- a/test-A/out.tsv
+++ b/test-A/out.tsv