Update README.md
Browse files
README.md
CHANGED
@@ -139,7 +139,7 @@ The two evaluation tasks make use of the [20 Minuten dataset](https://www.zora.u
|
|
139 |
|
140 |
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
141 |
|
142 |
-
Embeddings are computed for the summary and content of each document. Subsequently, the embeddings are matched by minimizing cosine similarity scores
|
143 |
|
144 |
The performance is measured via accuracy, i.e. the ratio of correct vs. incorrect matches. The script can be found [here](https://github.com/jgrosjean-mathesis/swissbert-for-sentence-embeddings/tree/main).
|
145 |
|
|
|
139 |
|
140 |
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
141 |
|
142 |
+
Embeddings are computed for the summary and content of each document. Subsequently, the embeddings are matched by minimizing cosine similarity scores between each summary and content embedding pair.
|
143 |
|
144 |
The performance is measured via accuracy, i.e. the ratio of correct vs. incorrect matches. The script can be found [here](https://github.com/jgrosjean-mathesis/swissbert-for-sentence-embeddings/tree/main).
|
145 |
|