explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-27 16:39:55 +03:00
Code Issues Packages Projects Releases Wiki Activity

clarify accuracy claim

Browse Source
This commit is contained in:
svlandeg 2023-09-08 10:16:37 +02:00
parent 6138e4cc0b
commit 06714404d2
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
website/docs/api/large-language-models.mdx
View File

@ -205,7 +205,6 @@ not require labels.
| ----------- | ------------------------------------------------------ | | ----------- | ------------------------------------------------------ |
| **RETURNS** | The labels added to the component. ~~Tuple[str, ...]~~ | | **RETURNS** | The labels added to the component. ~~Tuple[str, ...]~~ |
## Tasks {id="tasks"} ## Tasks {id="tasks"}
### Task implementation {id="task-implementation"} ### Task implementation {id="task-implementation"}
@ -316,8 +315,9 @@ The NER task identifies non-overlapping entities in text.
Version 3 is fundamentally different to v1 and v2, as it implements Version 3 is fundamentally different to v1 and v2, as it implements
Chain-of-Thought prompting, based on the Chain-of-Thought prompting, based on the
[PromptNER paper](https://arxiv.org/pdf/2305.15444.pdf) by Ashok and Lipton [PromptNER paper](https://arxiv.org/pdf/2305.15444.pdf) by Ashok and Lipton
(2023). From preliminary experiments, we've found this implementation to obtain (2023). On an internal use-case, we have found this implementation to obtain
significant better accuracy. significant better accuracy - with an increase of F-score of up to 15 percentage
points.
> #### Example config > #### Example config
> >