|
--- |
|
language: |
|
- en |
|
--- |
|
|
|
<div align="center"> |
|
<img src="https://github.com/SapienzaNLP/relik/blob/main/relik.png?raw=true" height="150"> |
|
<img src="https://github.com/SapienzaNLP/relik/blob/main/Sapienza_Babelscape.png?raw=true" height="50"> |
|
</div> |
|
|
|
<div align="center"> |
|
<h1>Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget</h1> |
|
</div> |
|
|
|
<div style="display:flex; justify-content: center; align-items: center; flex-direction: row;"> |
|
<a href="https://2024.aclweb.org/"><img src="http://img.shields.io/badge/ACL-2024-4b44ce.svg"></a> |
|
<a href="https://aclanthology.org/"><img src="http://img.shields.io/badge/paper-ACL--anthology-B31B1B.svg"></a> |
|
<a href="https://arxiv.org/abs/2408.00103"><img src="https://img.shields.io/badge/arXiv-2408.00103-b31b1b.svg"></a> |
|
</div> |
|
<div style="display:flex; justify-content: center; align-items: center; flex-direction: row;"> |
|
<a href="https://huggingface.co/collections/sapienzanlp/relik-retrieve-read-and-link-665d9e4a5c3ecba98c1bef19"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Collection-FCD21D"></a> |
|
<a href="https://github.com/SapienzaNLP/relik"><img src="https://img.shields.io/badge/GitHub-Repo-121013?logo=github&logoColor=white"></a> |
|
<a href="https://github.com/SapienzaNLP/relik/releases"><img src="https://img.shields.io/github/v/release/SapienzaNLP/relik"></a> |
|
</div> |
|
|
|
This model card is for a more lightweight index for the sapienzanlp/relik-retriever-e5-base-v2-aida-blink-encoder retriever. It contains the most popular 2M entities by their frequency across Wikipedia pages. |
|
|
|
A blazing fast and lightweight Information Extraction model for **Entity Linking** and **Relation Extraction**. |
|
|
|
**This repository contains the weights and the index for the Entity Linking ReLiK pipeline.** |
|
|
|
## 🛠️ Installation |
|
|
|
Installation from PyPI |
|
|
|
```bash |
|
pip install relik |
|
``` |
|
|
|
<details> |
|
<summary>Other installation options</summary> |
|
|
|
#### Install with optional dependencies |
|
|
|
Install with all the optional dependencies. |
|
|
|
```bash |
|
pip install relik[all] |
|
``` |
|
|
|
Install with optional dependencies for training and evaluation. |
|
|
|
```bash |
|
pip install relik[train] |
|
``` |
|
|
|
Install with optional dependencies for [FAISS](https://github.com/facebookresearch/faiss) |
|
|
|
FAISS PyPI package is only available for CPU. For GPU, install it from source or use the conda package. |
|
|
|
For CPU: |
|
|
|
```bash |
|
pip install relik[faiss] |
|
``` |
|
|
|
For GPU: |
|
|
|
```bash |
|
conda create -n relik python=3.10 |
|
conda activate relik |
|
|
|
# install pytorch |
|
conda install -y pytorch=2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia |
|
|
|
# GPU |
|
conda install -y -c pytorch -c nvidia faiss-gpu=1.8.0 |
|
# or GPU with NVIDIA RAFT |
|
conda install -y -c pytorch -c nvidia -c rapidsai -c conda-forge faiss-gpu-raft=1.8.0 |
|
|
|
pip install relik |
|
``` |
|
|
|
Install with optional dependencies for serving the models with |
|
[FastAPI](https://fastapi.tiangolo.com/) and [Ray](https://docs.ray.io/en/latest/serve/quickstart.html). |
|
|
|
```bash |
|
pip install relik[serve] |
|
``` |
|
|
|
#### Installation from source |
|
|
|
```bash |
|
git clone https://github.com/SapienzaNLP/relik.git |
|
cd relik |
|
pip install -e .[all] |
|
``` |
|
|
|
</details> |
|
|
|
## 🚀 Quick Start |
|
|
|
[//]: # (Write a short description of the model and how to use it with the `from_pretrained` method.) |
|
|
|
ReLiK is a lightweight and fast model for **Entity Linking** and **Relation Extraction**. |
|
It is composed of two main components: a retriever and a reader. |
|
The retriever is responsible for retrieving relevant documents from a large collection, |
|
while the reader is responsible for extracting entities and relations from the retrieved documents. |
|
ReLiK can be used with the `from_pretrained` method to load a pre-trained pipeline. |
|
|
|
Here is an example of how to use ReLiK for **Entity Linking**: |
|
|
|
```python |
|
from relik import Relik |
|
from relik.inference.data.objects import RelikOutput |
|
|
|
relik = Relik.from_pretrained("sapienzanlp/relik-entity-linking-large") |
|
relik_out: RelikOutput = relik("Michael Jordan was one of the best players in the NBA.") |
|
``` |
|
|
|
RelikOutput( |
|
text="Michael Jordan was one of the best players in the NBA.", |
|
tokens=['Michael', 'Jordan', 'was', 'one', 'of', 'the', 'best', 'players', 'in', 'the', 'NBA', '.'], |
|
id=0, |
|
spans=[ |
|
Span(start=0, end=14, label="Michael Jordan", text="Michael Jordan"), |
|
Span(start=50, end=53, label="National Basketball Association", text="NBA"), |
|
], |
|
triples=[], |
|
candidates=Candidates( |
|
span=[ |
|
[ |
|
[ |
|
{"text": "Michael Jordan", "id": 4484083}, |
|
{"text": "National Basketball Association", "id": 5209815}, |
|
{"text": "Walter Jordan", "id": 2340190}, |
|
{"text": "Jordan", "id": 3486773}, |
|
{"text": "50 Greatest Players in NBA History", "id": 1742909}, |
|
... |
|
] |
|
] |
|
] |
|
), |
|
) |
|
|
|
## 📊 Performance |
|
|
|
We evaluate the performance of ReLiK on Entity Linking using [GERBIL](http://gerbil-qa.aksw.org/gerbil/). The following table shows the results (InKB Micro F1) of ReLiK Large and Base: |
|
|
|
| Model | AIDA | MSNBC | Der | K50 | R128 | R500 | O15 | O16 | Tot | OOD | AIT (m:s) | |
|
|------------------------------------------|------|-------|------|------|------|------|------|------|------|------|------------| |
|
| GENRE | 83.7 | 73.7 | 54.1 | 60.7 | 46.7 | 40.3 | 56.1 | 50.0 | 58.2 | 54.5 | 38:00 | |
|
| EntQA | 85.8 | 72.1 | 52.9 | 64.5 | **54.1** | 41.9 | 61.1 | 51.3 | 60.5 | 56.4 | 20:00 | |
|
| [ReLiK<sub>Base<sub>](https://huggingface.co/sapienzanlp/relik-entity-linking-base) | 85.3 | 72.3 | 55.6 | 68.0 | 48.1 | 41.6 | 62.5 | 52.3 | 60.7 | 57.2 | 00:29 | |
|
| ➡️ [ReLiK<sub>Large<sub>](https://huggingface.co/sapienzanlp/relik-entity-linking-large) | **86.4** | **75.0** | **56.3** | **72.8** | 51.7 | **43.0** | **65.1** | **57.2** | **63.4** | **60.2** | 01:46 | |
|
|
|
Comparison systems' evaluation (InKB Micro F1) on the *in-domain* AIDA test set and *out-of-domain* MSNBC (MSN), Derczynski (Der), KORE50 (K50), N3-Reuters-128 (R128), |
|
N3-RSS-500 (R500), OKE-15 (O15), and OKE-16 (O16) test sets. **Bold** indicates the best model. |
|
GENRE uses mention dictionaries. |
|
The AIT column shows the time in minutes and seconds (m:s) that the systems need to process the whole AIDA test set using an NVIDIA RTX 4090, |
|
except for EntQA which does not fit in 24GB of RAM and for which an A100 is used. |
|
|
|
## 🤖 Models |
|
|
|
Models can be found on [🤗 Hugging Face](https://huggingface.co/collections/sapienzanlp/relik-retrieve-read-and-link-665d9e4a5c3ecba98c1bef19). |
|
|
|
## 💽 Cite this work |
|
|
|
If you use any part of this work, please consider citing the paper as follows: |
|
|
|
```bibtex |
|
@inproceedings{orlando-etal-2024-relik, |
|
title = "Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget", |
|
author = "Orlando, Riccardo and Huguet Cabot, Pere-Llu{\'\i}s and Barba, Edoardo and Navigli, Roberto", |
|
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024", |
|
month = aug, |
|
year = "2024", |
|
address = "Bangkok, Thailand", |
|
publisher = "Association for Computational Linguistics", |
|
} |
|
``` |
