Update README.md

README.md

@@ -108,35 +108,75 @@ ate_sent_pipeline(text_input)
 
 # Evaluation on Benchmark Test Datasets
 
+The first evaluation is for token-extraction task without considering the polarity of the extracted tokens. The tokens expected to be extracted are aspect term tokens
+on which the sentiments have been expressed. (scores are expressed as micro-averages of B-I-O labels)
+
 # ATE (Aspect Term Extraction Only)
 | Test Dataset | Base Model | Fine-tuned Model | Precision | Recall | F1 Score |
 | ------------ | ---------- | ---------------- | --------- | ------ | -------- |
 |hotel reviews (SemEval 2015)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|71.16|73.92|71.6|
-|hotel reviews (SemEval 2015)|FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|70.92|72.28|71.07|
+|hotel reviews (SemEval 2015)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|70.92|72.28|71.07|
 |hotel reviews (SemEval 2015)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|64.05|79.69|70.0|
 |hotel reviews (SemEval 2015)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|66.29|72.78|68.92|
 | ------------ | ---------- | ---------------- | --------- | ------ | -------- |
 |laptop reviews (SemEval 2014)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|70.58|61.52|64.21|
 |laptop reviews (SemEval 2014)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|66.38|50.62|54.31|
 |laptop reviews (SemEval 2014)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|70.82|48.97|52.08|
-|laptop reviews (SemEval 2014)|FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|73.61|46.38|49.87|
+|laptop reviews (SemEval 2014)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|73.61|46.38|49.87|
 | ------------ | ---------- | ---------------- | --------- | ------ | -------- |
 |MAMS-ATE (2019)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|81.07|79.66|80.35|
-|MAMS-ATE (2019)|FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|79.91|78.95|79.39|
+|MAMS-ATE (2019)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|79.91|78.95|79.39|
 |MAMS-ATE (2019)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|74.46|84.5|78.75|
 |MAMS-ATE (2019)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|77.8|79.81|78.75|
 | ------------ | ---------- | ---------------- | --------- | ------ | -------- |
 |restaurant reviews (SemEval 2014)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|88.59|87.0|87.45|
 |restaurant reviews (SemEval 2014)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|92.26|82.95|86.57|
-|restaurant reviews (SemEval 2014)|FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|93.07|81.95|86.32|
+|restaurant reviews (SemEval 2014)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|93.07|81.95|86.32|
 |restaurant reviews (SemEval 2014)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|92.94|81.71|86.01|
 | ------------ | ---------- | ---------------- | --------- | ------ | -------- |
 |restaurant reviews (SemEval 2015)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|72.91|75.4|72.74|
 |restaurant reviews (SemEval 2015)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|70.54|77.48|72.63|
 |restaurant reviews (SemEval 2015)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|68.32|79.84|72.28|
-|restaurant reviews (SemEval 2015)|FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|71.94|74.75|71.84|
+|restaurant reviews (SemEval 2015)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|71.94|74.75|71.84|
 | ------------ | ---------- | ---------------- | --------- | ------ | -------- |
 |restaurant reviews (SemEval 2016)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|70.22|75.83|71.84|
 |restaurant reviews (SemEval 2016)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|71.54|73.38|71.2|
-|restaurant reviews (SemEval 2016)|FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|71.35|72.78|70.85|
-|restaurant reviews (SemEval 2016)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|66.68|77.97|70.79|
+|restaurant reviews (SemEval 2016)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|71.35|72.78|70.85|
+|restaurant reviews (SemEval 2016)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|66.68|77.97|70.79|
+
+# Aspect Sentiment Evaluation
+This evaluation considers token-extraction task with polarity of the extracted tokens. The tokens expected to be extracted are aspect term tokens
+on which the sentiments have been expressed along with the polarity of the sentiments. (scores are expressed as macro-averages)
+| Test Dataset | Base Model | Fine-tuned Model | Precision | Recall | F1 Score |
+| ------------ | ---------- | ---------------- | --------- | ------ | -------- |
+|hotel reviews (SemEval 2015)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|51.92|65.55|54.94|
+|hotel reviews (SemEval 2015)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|54.62|53.65|54.08|
+|hotel reviews (SemEval 2015)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|55.43|56.53|54.03|
+|hotel reviews (SemEval 2015)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|52.88|55.19|53.85|
+| ------------ | ---------- | ---------------- | --------- | ------ | -------- |
+|laptop reviews (SemEval 2014)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|44.25|41.55|42.81|
+|laptop reviews (SemEval 2014)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|46.15|33.23|37.09|
+|laptop reviews (SemEval 2014)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|41.7|34.38|36.93|
+|laptop reviews (SemEval 2014)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|44.98|31.87|35.67|
+| ------------ | ---------- | ---------------- | --------- | ------ | -------- |
+|MAMS-ATE (2019)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|72.06|72.98|72.49|
+|MAMS-ATE (2019)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|72.97|71.63|72.26|
+|MAMS-ATE (2019)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|69.34|73.3|71.07|
+|MAMS-ATE (2019)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|65.74|75.11|69.77|
+| ------------ | ---------- | ---------------- | --------- | ------ | -------- |
+|restaurant reviews (SemEval 2014)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|61.15|58.46|59.74|
+|restaurant reviews (SemEval 2014)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|60.13|56.81|58.13|
+|restaurant reviews (SemEval 2014)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|56.79|59.3|57.93|
+|restaurant reviews (SemEval 2014)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|58.99|54.76|56.45|
+| ------------ | ---------- | ---------------- | --------- | ------ | -------- |
+|restaurant reviews (SemEval 2015)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|53.89|55.7|54.11|
+|restaurant reviews (SemEval 2015)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|54.36|55.38|53.6|
+|restaurant reviews (SemEval 2015)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|51.67|56.58|53.29|
+|restaurant reviews (SemEval 2015)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|54.55|53.68|53.12|
+| ------------ | ---------- | ---------------- | --------- | ------ | -------- |
+|restaurant reviews (SemEval 2016)|FacebookAI/roberta-large|[gauneg/roberta-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/roberta-large-absa-ate-sentiment-lora-adapter)|53.7|60.49|55.05|
+|restaurant reviews (SemEval 2016)|(this) FacebookAI/roberta-base|[gauneg/roberta-base-absa-ate-sentiment](https://huggingface.co/gauneg/roberta-base-absa-ate-sentiment)|52.31|54.58|52.33|
+|restaurant reviews (SemEval 2016)|microsoft/deberta-v3-base|[gauneg/deberta-v3-base-absa-ate-sentiment](https://huggingface.co/gauneg/deberta-v3-base-absa-ate-sentiment)|52.07|54.58|52.15|
+|restaurant reviews (SemEval 2016)|microsoft/deberta-v3-large|[gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter](https://huggingface.co/gauneg/deberta-v3-large-absa-ate-sentiment-lora-adapter)|49.07|56.5|51.25|
+
+