remove obsolete tests and links

README.md

@@ -85,6 +85,8 @@ The following is a list of related repositories that we like and think are usefu
 |[AzureML-BERT](https://github.com/Microsoft/AzureML-BERT)|End-to-end recipes for pre-training and fine-tuning BERT using Azure Machine Learning service.|
 |[MASS](https://github.com/microsoft/MASS)|MASS: Masked Sequence to Sequence Pre-training for Language Generation.|
 |[MT-DNN](https://github.com/namisan/mt-dnn)|Multi-Task Deep Neural Networks for Natural Language Understanding.|
+|[UniLM](https://github.com/microsoft/unilm)|Unified Language Model Pre-training.|
+
 
 
 ## Build Status

examples/text_classification/README.md

@@ -19,8 +19,5 @@ The following summarizes each notebook for Text Classification. Each notebook pr
 |Notebook|Environment|Description|Dataset|
 |---|---|---|---|
 |[BERT for text classification on AzureML](tc_bert_azureml.ipynb) |Azure ML|A notebook which walks through fine-tuning and evaluating pre-trained BERT model on a distributed setup with AzureML. |[MultiNLI](https://www.nyu.edu/projects/bowman/multinli/)|
-|[XLNet for text classification with MNLI](tc_mnli_xlnet.ipynb)|Local| A notebook which walks through fine-tuning and evaluating a pre-trained XLNet model on a subset of the MultiNLI dataset|[MultiNLI](https://www.nyu.edu/projects/bowman/multinli/)|
-|[BERT for text classification of Hindi BBC News](tc_bbc_bert_hi.ipynb)|Local| A notebook which walks through fine-tuning and evaluating a pre-trained BERT model on Hindi BBC news data|[BBC Hindi News](https://github.com/NirantK/hindi2vec/releases/tag/bbc-hindi-v0.1)|
-|[BERT for text classification of Arabic News](tc_dac_bert_ar.ipynb)|Local| A notebook which walks through fine-tuning and evaluating a pre-trained BERT model on Arabic news articles|[DAC](https://data.mendeley.com/datasets/v524p5dhpj/2)|
 |[Text Classification of MultiNLI Sentences using Multiple Transformer Models](tc_mnli_transformers.ipynb)|Local| A notebook which walks through fine-tuning and evaluating a number of pre-trained transformer models|[MultiNLI](https://www.nyu.edu/projects/bowman/multinli/)|
 |[Text Classification of Multi Language Datasets using Transformer Model](tc_multi_languages_transformers.ipynb)|Local|A notebook which walks through fine-tuning and evaluating a pre-trained transformer model for multiple datasets in different language|[MultiNLI](https://www.nyu.edu/projects/bowman/multinli/) <br> [BBC Hindi News](https://github.com/NirantK/hindi2vec/releases/tag/bbc-hindi-v0.1) <br> [DAC](https://data.mendeley.com/datasets/v524p5dhpj/2)

tests/integration/test_notebooks_text_classification.py

@@ -37,50 +37,6 @@ def test_tc_mnli_transformers(notebooks, tmp):
     assert pytest.approx(result["f1"], 0.89, abs=ABS_TOL)
 
 
-@pytest.mark.gpu
-@pytest.mark.integration
-def test_tc_dac_bert_ar(notebooks, tmp):
-    notebook_path = notebooks["tc_dac_bert_ar"]
-    pm.execute_notebook(
-        notebook_path,
-        OUTPUT_NOTEBOOK,
-        kernel_name=KERNEL_NAME,
-        parameters=dict(
-            NUM_GPUS=1,
-            DATA_FOLDER=tmp,
-            BERT_CACHE_DIR=tmp,
-            MAX_LEN=175,
-            BATCH_SIZE=16,
-            NUM_EPOCHS=1,
-            TRAIN_SIZE=0.8,
-            NUM_ROWS=8000,
-            RANDOM_STATE=0,
-        ),
-    )
-    result = sb.read_notebook(OUTPUT_NOTEBOOK).scraps.data_dict
-    assert pytest.approx(result["accuracy"], 0.871, abs=ABS_TOL)
-    assert pytest.approx(result["precision"], 0.865, abs=ABS_TOL)
-    assert pytest.approx(result["recall"], 0.852, abs=ABS_TOL)
-    assert pytest.approx(result["f1"], 0.845, abs=ABS_TOL)
-
-
-@pytest.mark.gpu
-@pytest.mark.integration
-def test_tc_bbc_bert_hi(notebooks, tmp):
-    notebook_path = notebooks["tc_bbc_bert_hi"]
-    pm.execute_notebook(
-        notebook_path,
-        OUTPUT_NOTEBOOK,
-        kernel_name=KERNEL_NAME,
-        parameters=dict(NUM_GPUS=1, DATA_FOLDER=tmp, BERT_CACHE_DIR=tmp, NUM_EPOCHS=1),
-    )
-    result = sb.read_notebook(OUTPUT_NOTEBOOK).scraps.data_dict
-    assert pytest.approx(result["accuracy"], 0.71, abs=ABS_TOL)
-    assert pytest.approx(result["precision"], 0.25, abs=ABS_TOL)
-    assert pytest.approx(result["recall"], 0.28, abs=ABS_TOL)
-    assert pytest.approx(result["f1"], 0.26, abs=ABS_TOL)
-
-
 @pytest.mark.integration
 @pytest.mark.azureml
 @pytest.mark.gpu
@@ -118,6 +74,7 @@ def test_tc_bert_azureml(
     if os.path.exists("outputs"):
         shutil.rmtree("outputs")
 
+
 @pytest.mark.gpu
 @pytest.mark.integration
 def test_multi_languages_transformer(notebooks, tmp):
@@ -126,10 +83,7 @@ def test_multi_languages_transformer(notebooks, tmp):
         notebook_path,
         OUTPUT_NOTEBOOK,
         kernel_name=KERNEL_NAME,
-        parameters={
-            "QUICK_RUN": True,
-            "USE_DATASET": "dac"
-        },
+        parameters={"QUICK_RUN": True, "USE_DATASET": "dac"},
     )
     result = sb.read_notebook(OUTPUT_NOTEBOOK).scraps.data_dict
     assert pytest.approx(result["precision"], 0.94, abs=ABS_TOL)