From 74bc144c7cc78fe11d11651578a66c50d66991ad Mon Sep 17 00:00:00 2001
From: zepingyu0512 <39480215+zepingyu0512@users.noreply.github.com>
Date: Tue, 6 Nov 2018 21:45:32 +0800
Subject: [PATCH] Update README.md

---
 README.md | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 446ca9f..ac97534 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # SRNN
 Author: Zeping Yu  <br />
-This work is accepted by COLING 2018. The paper could be downloaded at https://arxiv.org/ftp/arxiv/papers/1807/1807.02291.pdf <br /
+This work is accepted by COLING 2018. <br />
 [Sliced Recurrent Neural Network (SRNN)](https://arxiv.org/ftp/arxiv/papers/1807/1807.02291.pdf).  <br />
 SRNN is able to get much faster speed than standard RNN by slicing the sequences into many subsequences.  <br />
 The code is written in keras, using tensorflow backend. We implement the SRNN(8,2) here, and Yelp 2013 dataset is used.  <br />
@@ -8,7 +8,6 @@ keras version: 2.1.5 <br />
 tensorflow version: 1.6.0 <br />
 python : 2.7 <br />
 If you have any question, please contact me at zepingyu@foxmail.com. <br />
-If you think this work is OK, please star it:) <br />
 <br />
 The pre-trained GloVe word embeddings could be downloaded at:  <br /> 
 https://nlp.stanford.edu/projects/glove/ <br />