Papers
arxiv:2408.00103

ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget

Published on Jul 31
ยท Submitted by PereLluis13 on Aug 5
#3 Paper of the day

Abstract

Entity Linking (EL) and Relation Extraction (RE) are fundamental tasks in Natural Language Processing, serving as critical components in a wide range of applications. In this paper, we propose ReLiK, a Retriever-Reader architecture for both EL and RE, where, given an input text, the Retriever module undertakes the identification of candidate entities or relations that could potentially appear within the text. Subsequently, the Reader module is tasked to discern the pertinent retrieved entities or relations and establish their alignment with the corresponding textual spans. Notably, we put forward an innovative input representation that incorporates the candidate entities or relations alongside the text, making it possible to link entities or extract relations in a single forward pass and to fully leverage pre-trained language models contextualization capabilities, in contrast with previous Retriever-Reader-based methods, which require a forward pass for each candidate. Our formulation of EL and RE achieves state-of-the-art performance in both in-domain and out-of-domain benchmarks while using academic budget training and with up to 40x inference speed compared to competitors. Finally, we show how our architecture can be used seamlessly for Information Extraction (cIE), i.e. EL + RE, and setting a new state of the art by employing a shared Reader that simultaneously extracts entities and relations.

Community

Paper author Paper submitter

The paper presents a Retriever-Reader architecture for Entity Linking and Relation Extraction. First, entity and relations are retrieved from a Knowledge Base using the Retriever, from which topk are selected to be given to the Reader. Unlike previous work, the Reader is capable of linking spans of text to their corresponding entity as well as predicting the relations between them in a single forward pass. This is achieved by leveraging descriptive modeling, i.e. the candidate entities and relation types are given to the reader as part of the input, and then some specialized layers link spans to candidate entities, and predict relations between them. This image should explain this process visually:

Screenshot 2024-08-05 at 10.33.47.png

There is a collection of models released, a space demo, GitHub, pip package and Docker:

๐Ÿค— Check out our live demo on Huggingface: ReLiK Information Extraction

๐Ÿ“š Check out the model collection also on Huggingface: ReLiK Collection

๐Ÿ–ฅ Explore the code on GitHub: SapienzaNLP/ReLiK

๐Ÿ Python Package on PyPI

๐Ÿณ Docker images on Docker Hub

๐Ÿ“„ Read the full paper on Arxiv: ReLiK Paper

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 23

Browse 23 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2408.00103 in a dataset README.md to link it from this page.

Spaces citing this paper 2

Collections including this paper 7