From 67778600efe76475e57f360ec890da8861c1b8aa Mon Sep 17 00:00:00 2001
From: Nicholas Rempel <nick@lucent.is>
Date: Mon, 31 May 2021 10:09:22 -0700
Subject: [PATCH] Don't index English words

---
 instant-distance-py/examples/translations/translate.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/instant-distance-py/examples/translations/translate.py b/instant-distance-py/examples/translations/translate.py
index 85cbf78..085ecf0 100644
--- a/instant-distance-py/examples/translations/translate.py
+++ b/instant-distance-py/examples/translations/translate.py
@@ -68,6 +68,11 @@ async def download_build_index():
                         if lang == "en":
                             word_map[value] = embedding
                         else:
+                            # Don't index words that exist in english
+                            # to improve the quality of the results.
+                            if value in word_map:
+                                continue
+
                             # We track values here to build the instant-distance index
                             # Every value is prepended with 2 character language code.
                             # This allows us to determine language output later.