Update how-to-deploy-mlflow-models.md

Author: santiagxf

articles/machine-learning/how-to-deploy-mlflow-models.md

@@ -58,7 +58,7 @@ __MLmodel__
 
 :::code language="yaml" source="~/azureml-examples-main/sdk/python/endpoints/online/mlflow/sklearn-diabetes/model/MLmodel" highlight="13-19":::
 
-You can inspect the model signature of your model by opening the MLmodel file associated with your MLflow model. For more details about how signatures work in MLflow see [Signatures in MLflow](concept-mlflow-models.md#signatures).
+You can inspect the model signature of your model by opening the MLmodel file associated with your MLflow model. For more details about how signatures work in MLflow, see [Signatures in MLflow](concept-mlflow-models.md#signatures).
 
 > [!TIP]
 > Signatures in MLflow models are optional but they are highly encouraged as they provide a convenient way to early detect data compatibility issues. For more information about how to log models with signatures read [Logging models with a custom signature, environment or samples](how-to-log-mlflow-models.md#logging-models-with-a-custom-signature-environment-or-samples).
@@ -226,11 +226,11 @@ The previous payload corresponds to MLflow server 2.0+.
 
 ---
 
-For more information about MLflow built-in deployment tools see [MLflow documentation section](https://www.mlflow.org/docs/latest/models.html#built-in-deployment-tools).
+For more information about MLflow built-in deployment tools, see [MLflow documentation section](https://www.mlflow.org/docs/latest/models.html#built-in-deployment-tools).
 
 ## How to customize inference when deploying MLflow models
 
-You may be used to author scoring scripts to customize how inference is executed for your models. However, when deploying MLflow models to Azure Machine Learning, the decision about how inference should be executed is done by the model builder (the person who built the model) rather than by the DevOps engineer (the person who is trying to deploy it). Features like `autolog` in MLflow automatically log models for you as the best of the knowledge of the framework and that decisions may not be the ones you one in same scenarios.
+You may be used to author scoring scripts to customize how inference is executed for your models. However, when deploying MLflow models to Azure Machine Learning, the decision about how inference should be executed is done by the model builder (the person who built the model) rather than by the DevOps engineer (the person who is trying to deploy it). Features like `autolog` in MLflow automatically log models for you at the best of the knowledge of the framework. Those decisions may not be the ones you want in some scenarios.
 
 For those cases, you can either [change how your model is being logged in the training routine](#change-how-your-model-is-logged-during-training) or [customize inference with a scoring script](#customize-inference-with-a-scoring-script).
 
@@ -239,7 +239,7 @@ For those cases, you can either [change how your model is being logged in the tr
 
 When you log a model using either `mlflow.autolog` or using `mlflow.<flavor>.log_model`, the flavor used for the model decides how inference should be executed and what gets returned by the model. MLflow doesn't enforce any specific behavior in how the `predict()` function generates results. However, there are scenarios where you probably want to do some pre-processing or post-processing before and after your model is executed. On another scenarios, you may want to change what's returned like probabilities vs classes.
 
-A solution to this scenario is to implement machine learning pipelines that moves from inputs to outputs directly. For instance, [`sklearn.pipeline.Pipeline`](https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html) or [`pyspark.ml.Pipeline`](https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.ml.Pipeline.html) are very popular (and sometimes encourageable for performance considerations) ways to do so. Another alternative is to [customize how your model does inference using a custom model flavor](how-to-log-mlflow-models.md?#logging-custom-models).
+A solution to this scenario is to implement machine learning pipelines that moves from inputs to outputs directly. For instance, [`sklearn.pipeline.Pipeline`](https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html) or [`pyspark.ml.Pipeline`](https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.ml.Pipeline.html) are popular (and sometimes encourageable for performance considerations) ways to do so. Another alternative is to [customize how your model does inference using a custom model flavor](how-to-log-mlflow-models.md?#logging-custom-models).
 
 ### Customize inference with a scoring script