ehsk commited on
Commit
ca2af91
·
1 Parent(s): 5a1f47c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -3
README.md CHANGED
@@ -9,7 +9,16 @@ app_file: app.py
9
  pinned: false
10
  ---
11
 
12
- # Navigating ACL Papers via 2D Scatter Plots
13
- With the goal of understanding how scientific papers are related to one another, we plot their projections on a 2D plain in our interactive demo.
14
 
15
- To learn about how to generate plots like this, check out our step-by-step tutorial, [here](scipapers_scatter.ipynb).
 
 
 
 
 
 
 
 
 
 
 
9
  pinned: false
10
  ---
11
 
12
+ # Navigating ACL Anthology
 
13
 
14
+ With the goal of understanding how scientific papers are related to one another, we plot their projections on a 2D plain in our interactive [demo](https://huggingface.co/spaces/gwf-uwaterloo/acl-spectrum).
15
+
16
+ ## Data
17
+ We downloaded meta information of [ACL Anthology](https://aclanthology.org/) papers from [here](https://github.com/acl-org/acl-anthology/tree/master/data/xml).
18
+ Overall, 12,282 papers were derived from 4 conferences/journals, i.e. ACL (5.2K), EMNLP (4.6K), NAACL (2K), and TACL (442), over 7 years (2016-2023).
19
+
20
+ ## Embeddings
21
+ We encoded the papers (titles + abstracts) using [spectre2](https://huggingface.co/allenai/specter2_base), a BERT-based model designed for scientific literature.
22
+ We applied t-SNE to reduce dimensions for visualization.
23
+
24
+ 👉 To learn about how we generated the plot, check out our step-by-step guide [here](scipapers_scatter.ipynb).