Implement BLEU score evaluation for NLP tests - #6537

Add a new library for algorithmic NPL scoring evaluators, named Microsoft.Extensions.AI.Evaluation.NLP.

The first such evaluator that is implemented is BLEU. For this implementation we default to 4 even weights for the n-gram comparisons and we use the smoothing method 4 from Chen and Cherry (2014) for sentence-level BLEU scores. These are the same defaults chosen by the Azure python evaluation SDK.

Also included is a simple word tokenizer based on the tokenizers used for other BLEU implementations, such as MOSES, SacreBLEU and NLTK.

Microsoft Reviewers: Open in CodeFlow