Language and small clarifications.

README.md

@@ -35,7 +35,7 @@ The model was trained with the Adam Optimizer and a learning rate of 1e-5 with 1
 
 ### Intended uses & limitations
 
-This model is trained for document similarity tasks in biomedical scientific text using a single vector per document. Here, the documents are the title and abstract of a paper. With appropriate fine-tuning the model can also be used for other tasks such as classification. Since the training data comes primarily from biomedicine, performance on other domains may be poorer.
+This model is trained for document similarity tasks in **biomedical** scientific text using a single vector per document. Here, the documents are the title and abstract of a paper. With appropriate fine-tuning the model can also be used for other tasks such as classification. Since the training data comes primarily from biomedicine, performance on other domains may be poorer.
 
 ### How to use
 
@@ -56,19 +56,19 @@ clsrep = result.last_hidden_state[:,0,:]
 **`aspire-biencoder-biomed-scib-full`**, can be used as follows: 1) Download the [`aspire-biencoder-biomed-scib-full.zip`](https://drive.google.com/file/d/1MDCv9Fc33eP015HTWKi50WYXixh72h5c/view?usp=sharing), and 2) Use it per this example usage script: [`aspire/examples/ex_aspire_bienc.py`](https://github.com/allenai/aspire/blob/main/examples/ex_aspire_bienc.py)
 
 ### Variable and metrics
-This model is evaluated on information retrieval datasets with document level queries. Here we report performance on RELISH, and TRECCOVID. These are detailed on [github](https://github.com/allenai/aspire) and in our [paper](https://arxiv.org/abs/2111.08366). These datasets represent a abstract level retrieval task, where given a query scientific abstract the task requires the retrieval of relevant candidate abstracts. 
+This model is evaluated on information retrieval datasets with document level queries. Here we report performance on RELISH (biomedical/English), and TRECCOVID (biomedical/English). These are detailed on [github](https://github.com/allenai/aspire) and in our [paper](https://arxiv.org/abs/2111.08366). These datasets represent a abstract level retrieval task, where given a query scientific abstract the task requires the retrieval of relevant candidate abstracts. 
 
 We rank documents by the L2 distance between the query and candidate documents.
 
 ### Evaluation results
 
-The released model `aspire-biencoder-biomed-spec` (and `aspire-biencoder-biomed-spec-full`) is compared against `allenai/specter`. `aspire-biencoder-biomed-spec`<sup>*</sup> is the performance reported in our paper by averaging over 3 re-runs of the model. The released models `aspire-biencoder-biomed-spec` and `aspire-biencoder-biomed-spec-full` are the single best run among the 3 re-runs.
+The released model `aspire-biencoder-biomed-spec` (and `aspire-biencoder-biomed-spec-full`) is compared against `allenai/specter`. `aspire-biencoder-biomed-spec-full`<sup>*</sup> is the performance reported in our paper by averaging over 3 re-runs of the model. The released models `aspire-biencoder-biomed-spec` and `aspire-biencoder-biomed-spec-full` are the single best run among the 3 re-runs.
 
 |                                            | TRECCOVID  |    TRECCOVID    | RELISH  |     RELISH   |
 |-------------------------------------------:|:---------:|:-------:|:------:|:-------:|
 |                                            |    MAP    | NDCG%20 |   MAP  | NDCG%20 |
 |                               `specter`    |    28.24  | 59.28   |   60.62| 77.20   |
-| `aspire-biencoder-biomed-spec`<sup>*</sup> |    28.59  | 60.07   |   61.43| 77.96   |
+| `aspire-biencoder-biomed-spec-full`<sup>*</sup> |    28.59  | 60.07   |   61.43| 77.96   |
 |             `aspire-biencoder-biomed-spec` |    26.07  | 54.89   |   61.47| 78.34   |
 |        `aspire-biencoder-biomed-spec-full` |    28.87  | 60.47   |   61.69| 78.22   |