Add tokenizer exception for "gonna" (fixes #691)

2016-12-17 11:59:28 +01:00 · 2016-12-17 11:59:28 +01:00 · d8d50a0334
parent c69b77d8aa
commit d8d50a0334
1 changed files with 10 additions and 0 deletions
--- a/spacy/en/language_data.py
+++ b/spacy/en/language_data.py
@ -1493,6 +1493,16 @@ TOKENIZER_EXCEPTIONS = {
        {ORTH: "ma"}
    ],

+    "gonna": [
+        {ORTH: "gon", LEMMA: "go"},
+        {ORTH: "na", LEMMA: "to"}
+    ],
+
+    "Gonna": [
+        {ORTH: "Gon", LEMMA: "go"},
+        {ORTH: "na", LEMMA: "to"}
+    ],
+
    "whats": [
        {ORTH: "what"},
        {ORTH: "s"}