diff --git a/doc/design/distributed_lookup_table_design.md b/doc/design/distributed_lookup_table_design.md index 695a9831e21020f63e04d43900f93443a2ca9ba9..461b27a798cbde2f3684410577a0f9fd26fff929 100644 --- a/doc/design/distributed_lookup_table_design.md +++ b/doc/design/distributed_lookup_table_design.md @@ -2,7 +2,7 @@ ## Background -Embeddings is a popular technique used in neural network to support applications such as search engines, advertising systems, and recommendation systems. +Embedding is a popular technique used in neural network to support applications such as search engines, advertising systems, and recommendation systems. Embeddings are stored in a lookup table (or hash table), that given a word id, returns the embedding (which is an array of numbers).