diff --git a/main.py b/main.py
index 5c2cc1a11..b656b83e0 100644
--- a/main.py
+++ b/main.py
@@ -198,6 +198,13 @@ def poster(poster):
uid = poster
v = by_uid["papers"][uid]
data = _data()
+
+ data["openreview"] = format_paper(by_uid["papers"][uid])
+ data["id"] = uid
+ data["paper_recs"] = [
+ format_paper(by_uid["papers"][n]) for n in site_data["paper_recs"][uid]
+ ][1:]
+
data["paper"] = format_paper(v)
return render_template("poster.html", **data)
diff --git a/scripts/README.md b/scripts/README.md
index 3aec96e8e..34b4c752a 100644
--- a/scripts/README.md
+++ b/scripts/README.md
@@ -1,5 +1,8 @@
This directory contains extensions to help support the mini-conf library.
+For the updated procedure on getting similar papers + recommendations refer to README.recommendations.md
+
+
These include:
* `embeddings.py` : For turning abstracts into embeddings. Creates an `embeddings.torch` file.
@@ -17,7 +20,7 @@ python3 scripts/generate_version.py build/version.json
* `reduce.py` : For creating two-dimensional representations of the embeddings.
```bash
-python embeddings.py ../sitedata/papers.csv embeddings.torch > ../sitedata/papers_projection.json
+python reduce.py ../sitedata/papers.csv embeddings.torch > ../sitedata/papers_projection.json --projection-method umap
```
* `parse_calendar.py` : to convert a local or remote ICS file to JSON. -- more on importing calendars see [README_Schedule.md](README_Schedule.md)
diff --git a/scripts/README.recommendations.md b/scripts/README.recommendations.md
new file mode 100644
index 000000000..6d76fc8ac
--- /dev/null
+++ b/scripts/README.recommendations.md
@@ -0,0 +1,35 @@
+# How to get similar paper recommendations
+
+In this guide we can see how to get paper recommendations using the pretrained model provided
+from [ICLR webpage](https://github.com/ICLR/iclr.github.io/tree/master/recommendations) and abstract embeddings.
+
+
+
+## Create a visualization based on BERT embeddings
+
+1. Grab ACL2020
+ [papers.csv](https://github.com/acl-org/acl-2020-virtual-conference-sitedata/blob/add_acl2020_accepted_papers_tsv/papers.csv)
+ from this branch or a more recent version and copy it to `sitedata_acl2020`.
+2. Run `python scripts/embeddings.py sitedata_acl2020/papers.csv` to produce the BERT embeddings
+ for the paper abstracts.
+3. Run `python scripts/reduce.py --projection-method [tsne|umap] sitedata_acl2020/papers.csv embeddings.torch > sitedata_acl2020/papers_projection.json`
+ to produce a 2D projection of the BERT embeddings for visualization. `--projection-method`
+ selects which dimensionality reduction technique to use.
+4. Rerun `make run` and go to the paper visualization page
+
+
+## Produce similar paper recommendations
+
+1. Run `python scripts/create_recommendations_pickle.py --inp sitedata_acl2020/papers.csv --out cached_or.pkl` to produce `cached_or.pkl`.
+ This file is compatible with the inference scripts provided in [https://github.com/ICLR/iclr.github.io/tree/master/recommendations](https://github.com/ICLR/iclr.github.io/tree/master/recommendations)
+2. Clone [https://github.com/ICLR/iclr.github.io](https://github.com/ICLR/iclr.github.io). You will
+ need `git-lfs` installed.
+3. `cp cached_or.pkl iclr.github.io && cd iclr.github.io/recommendations`
+4. Install missing requirements
+5. `python recs.py`. This will run inference using a pretrained similarity model and produce the
+ `rec.pkl` file that contains the paper similarities.
+6. You can use the `iclr.github.io/data/pkl_to_json.py` script to produce the `paper_recs.json`
+ file that contains the similar paper recommendations that can be displayed to the website. Make
+ sure to modify the filepaths to point to the correct `cached_or.pkl`, `rec.pkl`.
+7. Grab the produced `paper_recs.json` file and copy it to `sitedata_acl2020`. A version of this file
+ produced using this method is [here](https://github.com/acl-org/acl-2020-virtual-conference-sitedata/blob/add_acl2020_accepted_papers_tsv/paper_recs.json)
diff --git a/scripts/create_recommendations_pickle.py b/scripts/create_recommendations_pickle.py
new file mode 100644
index 000000000..dea19581a
--- /dev/null
+++ b/scripts/create_recommendations_pickle.py
@@ -0,0 +1,50 @@
+import argparse
+import csv
+import pickle
+
+import openreview # type: ignore
+
+# No type hints for openreview-py package. Ignore mypy
+
+
+def read_entries(papers_csv):
+ with open(papers_csv, "r") as fd:
+ entries = list(csv.reader(fd, skipinitialspace=True))
+ entries = entries[1:] # skip header
+
+ return entries
+
+
+def dump_cached_or(entries, out_pickle):
+ cached_or = {}
+ for entry in entries:
+ cached_or[entry[0]] = openreview.Note( # id
+ "", [], [], [], {"abstract": entry[3], "title": entry[1]}
+ ) # Hack. ICLR Recommender script accepts Openreview notes
+
+ with open(out_pickle, "wb") as fd:
+ pickle.dump(cached_or, fd)
+
+
+def parse_args():
+ parser = argparse.ArgumentParser(
+ description="Convert CSV from original ACL format to Miniconf "
+ "compatible format"
+ )
+ parser.add_argument("--inp", type=str, help="papers.csv")
+ parser.add_argument(
+ "--out",
+ type=str,
+ help="Dump entries into a pickle compatible with " "ICLR Recommendation engine",
+ )
+ return parser.parse_args()
+
+
+def main():
+ args = parse_args()
+ entries = read_entries(args.inp)
+ dump_cached_or(entries, args.out)
+
+
+if __name__ == "__main__":
+ main()
diff --git a/scripts/reduce.py b/scripts/reduce.py
index 9d69fb9ab..5fd1d4805 100644
--- a/scripts/reduce.py
+++ b/scripts/reduce.py
@@ -4,6 +4,9 @@
import sklearn.manifold
import torch
+import umap # type: ignore
+
+# No type stubs for umap-learn. Ignore mypy
def parse_arguments():
@@ -11,6 +14,7 @@ def parse_arguments():
parser.add_argument("papers", default=False, help="paper file")
parser.add_argument("embeddings", default=False, help="embeddings file to shrink")
+ parser.add_argument("--projection-method", default="tsne", help="[umap|tsne]")
return parser.parse_args()
@@ -18,7 +22,16 @@ def parse_arguments():
if __name__ == "__main__":
args = parse_arguments()
emb = torch.load(args.embeddings)
- out = sklearn.manifold.TSNE(n_components=2).fit_transform(emb.numpy())
+ if args.projection_method == "tsne":
+ out = sklearn.manifold.TSNE(n_components=2).fit_transform(emb.numpy())
+ elif args.projection_method == "umap":
+ out = umap.UMAP(
+ n_neighbors=5, min_dist=0.3, metric="correlation", n_components=2
+ ).fit_transform(emb.numpy())
+ else:
+ print("invalid projection-method: {}".format(args.projection_method))
+ print("Falling back to T-SNE")
+ out = sklearn.manifold.TSNE(n_components=2).fit_transform(emb.numpy())
d = []
with open(args.papers, "r") as f:
abstracts = list(csv.DictReader(f))
diff --git a/scripts/requirements.txt b/scripts/requirements.txt
index 01bfdcd3c..0da07c264 100644
--- a/scripts/requirements.txt
+++ b/scripts/requirements.txt
@@ -1,4 +1,6 @@
transformers
sklearn
+umap-learn
+openreview-py
torch==1.4.0
ics
diff --git a/templates/poster.html b/templates/poster.html
index b673d38cb..e199c2ca8 100644
--- a/templates/poster.html
+++ b/templates/poster.html
@@ -139,6 +139,33 @@
