metadata

title: acl-spectrum
emoji: 📊
colorFrom: gray
colorTo: pink
sdk: streamlit
sdk_version: 1.26.0
app_file: app.py
pinned: false
license: mit

Navigating ACL Anthology

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.

Data

We downloaded meta information of ACL Anthology papers from here.

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).

Embeddings

We encoded the papers (titles + abstracts) using spectre2, a BERT-based model designed for scientific literature. We applied t-SNE to reduce dimensions for visualization.

To learn about how we generated the plot, check out our step-by-step guide here.

👉 Released under the MIT License.

👉 For questions (❓), problems (🛠️), or bug reports (🐛), please open an issue under the Community tab.