L

Lilt Roberta En Base

Developed by SCUT-DLVCLab
Language-independent Layout Transformer (LiLT) provides a LayoutLM-like model for any language by combining pre-trained RoBERTa (English) with a pre-trained language-independent layout transformer (LiLT).
Downloads 12.05k
Release Time : 9/29/2022

Model Overview

This model is designed for fine-tuning on tasks such as document image classification, document parsing, and document question answering, supporting multilingual document understanding.

Model Features

Language-agnostic
Can be combined with RoBERTa models in any language to support multilingual document understanding
Lightweight Layout Transformer
The LiLT module is lightweight and efficient, focusing on processing document layout information
Pre-trained model compatibility
Can be used with any pre-trained RoBERTa encoder available in the Hub

Model Capabilities

Document image classification
Document parsing
Document question answering
Structured document understanding

Use Cases

Document processing
Invoice processing
Extract key information from multilingual invoices
Table parsing
Parse tabular data in complex documents
Smart office
Contract analysis
Automatically analyze key clauses in contract documents
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase