Commit
•
4f42d19
1
Parent(s):
9c3e833
Update README.md
Browse files
README.md
CHANGED
@@ -1,13 +1,31 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
pipeline_tag:
|
4 |
---
|
5 |
|
|
|
|
|
6 |
Passage Re-Ranker a encoder based model that takes a search query, and a passage, and calculates the relevancy of the passage to the query. This is used in conjunction with sentence transformers to re-rank the passages matched by the sentence transformer, there-by improving relevance of Information Retrieval processes.
|
7 |
|
8 |
The Model is Finetuned using MS-Marco, and tested using Science QA datasets.
|
9 |
|
10 |
The Model is an integral part of `Neural Search` Information Retreival process used by the Science Discovery Engine, Along with the finetuned sentence transformer (https://huggingface.co/nasa-impact/nasa-smd-ibm-st-v2).
|
11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
pipeline_tag: text-classification
|
4 |
---
|
5 |
|
6 |
+
|
7 |
+
## Description:
|
8 |
Passage Re-Ranker a encoder based model that takes a search query, and a passage, and calculates the relevancy of the passage to the query. This is used in conjunction with sentence transformers to re-rank the passages matched by the sentence transformer, there-by improving relevance of Information Retrieval processes.
|
9 |
|
10 |
The Model is Finetuned using MS-Marco, and tested using Science QA datasets.
|
11 |
|
12 |
The Model is an integral part of `Neural Search` Information Retreival process used by the Science Discovery Engine, Along with the finetuned sentence transformer (https://huggingface.co/nasa-impact/nasa-smd-ibm-st-v2).
|
13 |
|
14 |
+
## Evaluation:
|
15 |
+
|
16 |
+
Model Evaluation on msmarco dev set, and NASA Science Questions:
|
17 |
+
|
18 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/jJnEkMijBvnTSN_cb_lDn.png)
|
19 |
+
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
Both query and passagehave to fit in 512 Tokens. The intended use is to rerank the first dozens of embedding search results.
|
24 |
+
|
25 |
+
## How to use
|
26 |
|
27 |
+
```
|
28 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
29 |
+
tokenizer = AutoTokenizer.from_pretrained("nasa-impact/nasa-smd-ibm-ranker")
|
30 |
+
model = AutoModelForSequenceClassification.from_pretrained("nasa-impact/nasa-smd-ibm-ranker")
|
31 |
+
```
|