Update README.md

README.md

@@ -35,7 +35,17 @@ More information needed
 
 ## Training procedure
 
-### Training hyperparameters
+the overall idea of our approach is to disentangle each dream report from its annotation as a whole and to create an augmented set of (dream report; single 
+feature annotation). To make sure that, given the same report, the model would produce a specific HVDC feature, we simply append at 
+the beginning of each report a string of the form ``HVDC-Feature :'', in a manner that closely mimics T5 task-specific prefix fine-tuning. 
+
+After this procedure to the original dataset (\~1.8K) we obtain approximately 6.6K items. %For this work, we focused on six HVDC features, namely Characters, Activities, Emotion, Friendliness, Misfortune, and Good Fortune. We did so to exclude features that amounted to less than 10\% of the total instance. Indeed, this would have excluded \texttt{Good Fortune} (see Figure \ref{fig:train_set_prefix_dist}). We include either way the feature to control for memorisation and counterbalance the \texttt{Misfortune} feature. 
+In the present study, we focused on a subset of six HVDC features: Characters, Activities, Emotion, Friendliness, Misfortune, and Good Fortune. This selection was made to exclude features that represented less than 10\% of the total instances. Notably, \texttt{Good Fortune} would have been excluded under this criterion (refer to Figure \ref{fig:train_set_prefix_dist}), but we intentionally retained this feature to control against potential memorisation effects and to provide a counterbalance to the \texttt{Misfortune} feature. After filtering out instances whose annotation feature is not one of the six selected features, we are left with \~5.3K %5389 
+dream reports. We then generate a random split of 80\%-20\% for the training (i.e 4,311 reports) and testing (i.e. 1,078 reports) sets.
+
+### Training
+
+#### Hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
@@ -49,7 +59,7 @@ The following hyperparameters were used during training:
 - mixed_precision_training: Native AMP
 - label_smoothing_factor: 0.1
 
-### Training results
+#### Metrics
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
@@ -78,15 +88,21 @@ The following hyperparameters were used during training:
 
 We selected the best model via validation loss. The table below reposts overall and feature-specific scores.
 
-| Feature      |   Rouge1 |   Rouge2 |   RougeL |   RougeLsum |
+| Feature      |   rouge1 |   rouge2 |   rougeL |   rougeLsum |
 |:-------------|---------:|---------:|---------:|------------:|
-| Activities   |  72.0539 |  59.8038 |  66.3395 |     66.3178 |
-| Characters   |  90.8584 |  86.1662 |  88.5297 |     88.4876 |
-| Emotion      |  85.2599 |  77.1463 |  84.688  |     84.7124 |
-| Friendliness |  74.3159 |  60.518  |  70.3793 |     70.3525 |
-| Good Fortune |  79.1209 |  11.5385 |  78.5714 |     78.5714 |
-| Misfortune   |  65.5146 |  48.8599 |  65.3226 |     65.1807 |
-| Overall      |  83.053  |  72.5731 |  80.8008 |     80.8026 |
+| Activities   |     72.1 |     59.8 |     66.3 |        66.3 |
+| Characters   |     90.9 |     86.2 |     88.5 |        88.5 |
+| Emotion      |     85.3 |     77.1 |     84.7 |        84.7 |
+| Friendliness |     74.3 |     60.5 |     70.4 |        70.4 |
+| Good Fortune |     79.1 |     11.5 |     78.6 |        78.6 |
+| Misfortune   |     65.5 |     48.9 |     65.3 |        65.2 |
+| Overall      |     83.1 |     72.6 |     80.8 |        80.8 |
+
+### Disclaimer
+Dream reports and their annotation have been used in clinical settings and applied for diagnostic purposes. 
+This does not apply in any way to our experimental results and output. 
+Our work aims to provide experimental evidence of the feasibility of using PLMs to support humans
+in annotating dream reports for research purposes, as well as detailing their strengths and limitations when approaching such a task.
 
 ### Framework versions