From 3916730959ababb3d3a9c1b2901e3283fe0dbc61 Mon Sep 17 00:00:00 2001 From: hsm207 Date: Tue, 9 Apr 2019 20:05:20 +0800 Subject: [PATCH] Fix formatting --- README.md | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 4e67d72..394d21f 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -#Retrofitting +# Retrofitting Manaal Faruqui, manaalfar@gmail.com This tool is used to post-process word vectors to incorporate @@ -7,11 +7,11 @@ these word vectors are generally better in performance on semantic tasks than the original word vectors. This tool can be used for word vectors obtained from any vector training model. -###Requirements +### Requirements 1. Python 2.7 -###Data you need +### Data you need 1. Word vector file 2. Lexicon file (provided here) @@ -19,7 +19,7 @@ Each vector file should have one word vector per line as follows (space delimite ```the -1.0 2.4 -0.3 ...``` -###Running the program +### Running the program ```python retrofit.py -i word_vec_file -l lexicon_file -n num_iter -o out_vec_file``` @@ -28,12 +28,12 @@ Each vector file should have one word vector per line as follows (space delimite where, 'n' is an integer which specifies the number of iterations for which the optimization is to be performed. Usually n = 10 gives reasonable results. -###Output +### Output File: ```out_vec.txt``` which are your new retrofitted and (hopefully) improved word vectors, enjoy ! -###Reference +### Reference Main paper to be cited ``` @@ -46,4 +46,3 @@ Main paper to be cited ``` If you are using PPDB (Ganitkevitch et al, 2013), WordNet (Miller, 1995) or FrameNet (Baker et al, 1998) for enrichment please cite the corresponding papers. -