Update README.md

rtroncy · web-flow · commit 0e5bc285c07d · 2021-03-14T11:28:00.000+01:00
Improve README in clarifying the role of each notebooks
diff --git a/README.md b/README.md
@@ -1,16 +1,16 @@
 # GraphNER
 
-This repository contains the preliminary code for reproducing the results reported in the paper "[GraphNER: Named Entity Recognition as Graph Classification](https://openreview.net/forum?id=vfpW-kRvLgu)" (currently under review).
+This repository contains the code for reproducing the preliminary results reported in the paper "[Named Entity Recognition as Graph Classification](https://openreview.net/forum?id=QA_Ttxv9WfG)" (currently under review for the [ESWC 2021 Poster Track conference](https://2021.eswc-conferences.org/)).
 
 ## Overview
 The code is organized as notebooks, to be used as follows:
-* `final_generate_gazetteers.ipynb`: to generate the gazeteers from Wikidata (by specifying a list of QIDs corresponding to the classes)
-* `edge_list_generation.ipynb`: to generate the graph structure to build the graph embeddings
-* `graph_embeddings_generation.ipynb`: to generate node embeddings using [GEM library](https://github.com/palash1992/GEM) algorithms (e.g. node2ve, SDNE..)
+* `final_generate_gazetteers.ipynb`: to generate gazeteers from Wikidata (by specifying a list of QIDs corresponding to the entity types that one wishes to extract)
+* `edge_list_generation.ipynb`: to generate the graph structure to build the graph embeddings; when applied to the [ConLL 2003 train dataset](https://www.clips.uantwerpen.be/conll2003/ner/), one should get a similar result that this [Python dict data structure](https://github.com/Siliam/graph_ner/blob/main/dataset/conll/conll_graph.pickle)
+* `graph_embeddings_generation.ipynb`: to generate node embeddings using of the algorithms (e.g. node2ve, SDNE..) provided by the [GEM library](https://github.com/palash1992/GEM)
 * `nodes_classifier.ipynb`: to train a model for the node embeddings
 * `autoencoder_embeddings.ipynb`: to generate auto-encoder embeddings from the binary graph representations
 * `autoencoder_nn_classification.ipynb`: to train a model for the auto-encoder embeddings
-* `GCN-node-simple-features.ipynb`: to train a GCN on the CoNLL-2003 task
+* `GCN-node-simple-features.ipynb`: to train a GCN on the CoNLL-2003 dataset
 
 The code will be streamlined into stand-alone configurable scripts and fully documented soon.
 
@@ -27,7 +27,7 @@ The code will be streamlined into stand-alone configurable scripts and fully doc
 :warning:	This code runs on a CUDA11.0-enabled GPU, please install the compatible version of the modules for your hardware.
 
 ## Results
-The table below shows the performance of different models on the validation set of CoNLL-2003
+The table below shows the performance of different models on the validation set (dev) of [CoNLL-2003](https://www.clips.uantwerpen.be/conll2003/ner/)
 
 Method           | Accuracy | Micro-F1 | Macro-F1 
 -----------------|----------|----------|---------
