fittar commited on
Commit
90fcc4b
·
1 Parent(s): 63ed74b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -30,7 +30,7 @@ in generating depictable and semantically meaningful prompts.
30
  <!-- Provide the basic links for the model. -->
31
 
32
  - **Repository:** [Github](https://github.com/Hazel1994/ViPE)
33
- - **Paper:** [ViPE: Visualise Pretty-much Everything, EMNLP2023](https://arxiv.org/abs/2310.10543)
34
 
35
  ### Down Stream Applications
36
  ViPE provides a robust backbone for many practical applications such as music video generation and creative writing.
@@ -103,7 +103,7 @@ However, a semicolon draws a stronger boundary between the keywords and encourag
103
  ### Training Data
104
 
105
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
106
- - LyricCanvas dataset: a synthetically generated dataset: will be published soon
107
 
108
  ### Training Procedure
109
 
 
30
  <!-- Provide the basic links for the model. -->
31
 
32
  - **Repository:** [Github](https://github.com/Hazel1994/ViPE)
33
+ - **Paper:** [ViPE: Visualise Pretty-much Everything](https://aclanthology.org/2023.emnlp-main.333/) (**Outstanding Paper Award at EMNLP 2023**)
34
 
35
  ### Down Stream Applications
36
  ViPE provides a robust backbone for many practical applications such as music video generation and creative writing.
 
103
  ### Training Data
104
 
105
  <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
106
+ - LyricCanvas dataset: a synthetically generated dataset based on lyrics and synthetically generated prompts
107
 
108
  ### Training Procedure
109