wehub-resource-sync
103 lines
4.9 KiB
Markdown
103 lines
4.9 KiB
Markdown
<!--[metadata]
|
|
title = "LLM embedding-based named entity recognition"
|
|
tags = ["LLM", "Embeddings", "Classification", "Hugging Face", "Text"]
|
|
thumbnail = "https://static.rerun.io/llm-embedding/999737b3b78d762e70116bc23929ebfde78e18c6/480w.png"
|
|
thumbnail_dimensions = [480, 480]
|
|
-->
|
|
|
|
Visualize the [BERT-based named entity recognition (NER)](https://huggingface.co/dslim/bert-base-NER) with UMAP Embeddings.
|
|
|
|
<picture>
|
|
<img src="https://static.rerun.io/llm_embedding_ner/d98c09dd6bfa20ceea3e431c37dc295a4009fa1b/full.png" alt="">
|
|
<source media="(max-width: 480px)" srcset="https://static.rerun.io/llm_embedding_ner/d98c09dd6bfa20ceea3e431c37dc295a4009fa1b/480w.png">
|
|
<source media="(max-width: 768px)" srcset="https://static.rerun.io/llm_embedding_ner/d98c09dd6bfa20ceea3e431c37dc295a4009fa1b/768w.png">
|
|
<source media="(max-width: 1024px)" srcset="https://static.rerun.io/llm_embedding_ner/d98c09dd6bfa20ceea3e431c37dc295a4009fa1b/1024w.png">
|
|
<source media="(max-width: 1200px)" srcset="https://static.rerun.io/llm_embedding_ner/d98c09dd6bfa20ceea3e431c37dc295a4009fa1b/1200w.png">
|
|
</picture>
|
|
|
|
## Used Rerun types
|
|
[`TextDocument`](https://www.rerun.io/docs/reference/types/archetypes/text_document), [`AnnotationContext`](https://www.rerun.io/docs/reference/types/archetypes/annotation_context), [`Points3D`](https://www.rerun.io/docs/reference/types/archetypes/points3d)
|
|
|
|
## Background
|
|
This example splits text into tokens, feeds the token sequence into a large language model (BERT), which outputs an embedding per token.
|
|
The embeddings are then classified into four types of entities: location (LOC), organizations (ORG), person (PER) and Miscellaneous (MISC). The embeddings are projected to a 3D space using [UMAP](https://umap-learn.readthedocs.io/en/latest), and visualized together with all other data in Rerun.
|
|
|
|
## Logging and visualizing with Rerun
|
|
The visualizations in this example were created with the following Rerun code:
|
|
|
|
### Text
|
|
The logging begins with the original text. Following this, the tokenized version is logged for further analysis, and the named entities identified by the NER model are logged separately.
|
|
All texts are logged using [`TextDocument`](https://www.rerun.io/docs/reference/types/archetypes/text_document) as a Markdown document to preserves structure and formatting.
|
|
|
|
#### Original text
|
|
```python
|
|
rr.log("text", rr.TextDocument(text, media_type=rr.MediaType.MARKDOWN))
|
|
```
|
|
|
|
#### Tokenized text
|
|
```python
|
|
rr.log("tokenized_text", rr.TextDocument(markdown, media_type=rr.MediaType.MARKDOWN))
|
|
```
|
|
|
|
#### Named entities
|
|
```python
|
|
rr.log("named_entities", rr.TextDocument(named_entities_str, media_type=rr.MediaType.MARKDOWN))
|
|
```
|
|
|
|
### UMAP embeddings
|
|
|
|
UMAP is used in this example for dimensionality reduction and visualization of the embeddings generated by a Named Entity Recognition (NER) model.
|
|
UMAP preserves the essential structure and relationships between data points, and helps in identifying clusters or patterns within the named entities.
|
|
|
|
After transforming the embeddings to UMAP, the next step involves defining labels for classes using [`AnnotationContext`](https://www.rerun.io/docs/reference/types/archetypes/annotation_context).
|
|
These labels help in interpreting the visualized data.
|
|
Subsequently, the UMAP embeddings are logged as [`Points3D`](https://www.rerun.io/docs/reference/types/archetypes/points3d) and visualized in a three-dimensional space.
|
|
The visualization can provide insights into how the NER model is performing and how different types of entities are distributed throughout the text.
|
|
|
|
|
|
```python
|
|
# Define label for classes and set none class color to dark gray
|
|
annotation_context = [
|
|
rr.AnnotationInfo(id=0, color=(30, 30, 30)),
|
|
rr.AnnotationInfo(id=1, label="Location"),
|
|
rr.AnnotationInfo(id=2, label="Person"),
|
|
rr.AnnotationInfo(id=3, label="Organization"),
|
|
rr.AnnotationInfo(id=4, label="Miscellaneous"),
|
|
]
|
|
rr.log("/", rr.AnnotationContext(annotation_context))
|
|
```
|
|
|
|
```python
|
|
rr.log(
|
|
"umap_embeddings",
|
|
rr.Points3D(umap_embeddings, class_ids=class_ids),
|
|
rr.AnyValues(**{"Token": token_words, "Named Entity": entity_per_token(token_words, ner_results)}),
|
|
)
|
|
```
|
|
|
|
|
|
## Run the code
|
|
To run this example, make sure you have the Rerun repository checked out and the latest SDK installed:
|
|
```bash
|
|
pip install --upgrade rerun-sdk # install the latest Rerun SDK
|
|
git clone git@github.com:rerun-io/rerun.git # Clone the repository
|
|
cd rerun
|
|
git checkout latest # Check out the commit matching the latest SDK release
|
|
```
|
|
Install the necessary libraries specified in the requirements file:
|
|
```bash
|
|
pip install -e examples/python/llm_embedding_ner
|
|
```
|
|
To experiment with the provided example, simply execute the main Python script:
|
|
```bash
|
|
python -m llm_embedding_ner # run the example
|
|
```
|
|
You can specify your own text using:
|
|
```bash
|
|
python -m llm_embedding_ner [--text TEXT]
|
|
```
|
|
If you wish to customize it, explore additional features, or save it use the CLI with the `--help` option for guidance:
|
|
```bash
|
|
python -m llm_embedding_ner --help
|
|
```
|