Minor changes

README.md

@@ -47,12 +47,12 @@ Further, since the model relies on computing a document-document scores via a Wa
 
 This code uses the [`geomloss`](https://www.kernel-operations.io/geomloss/api/pytorch-api.html) library for computing Wasserstein distances.
 
-(Additional example code to demo this more will be added in the next couple days!)
+(Additional example code to demo this more will be added in the coming weeks!)
 
 ### Variable and metrics
 This model is evaluated on information retrieval datasets with document level queries. Performance here is reported on CSFCube (computer science/English). This is detailed on [github](https://github.com/allenai/aspire) and in our [paper](https://arxiv.org/abs/2111.08366). CSFCube presents a finer-grained query via selected sentences in a query abstract based on which a finer-grained retrieval must be made from candidate abstracts.
 
-In using this model we rank documents by the minimal Wasserstein distance between the query sentences and a candidates sentences.
+In using this model we rank documents by the Wasserstein distance between the query sentences and a candidates sentences.
 
 ### Evaluation results