From b9b11795cfdce7bb8dd8a01ec5efa602589a78b2 Mon Sep 17 00:00:00 2001 From: Xin Wen Date: Mon, 27 Jul 2020 17:34:02 +0800 Subject: [PATCH] Update model_summary.rst (#5737) Add '-' to make the reference of Transformer-XL more accurate and formal. --- docs/source/model_summary.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/model_summary.rst b/docs/source/model_summary.rst index f87a488f2..5371492de 100644 --- a/docs/source/model_summary.rst +++ b/docs/source/model_summary.rst @@ -195,7 +195,7 @@ tokens in the sentence, then allows the model to use the last n tokens to predic with a mask, the sentence is actually fed in the model in the right order, but instead of masking the first n tokens for n+1, XLNet uses a mask that hides the previous tokens in some given permutation of 1,...,sequence length. -XLNet also uses the same recurrence mechanism as TransformerXL to build long-term dependencies. +XLNet also uses the same recurrence mechanism as Transformer-XL to build long-term dependencies. The library provides a version of the model for language modeling, token classification, sentence classification, multiple choice classification and question answering.