xlm-roberta-large-ner-hrl Open-source Named Entity Recognition Model - Supports Location, Organization, and Person Recognition in 10 Languages

Xlm Roberta Large Ner Hrl

Developed by Davlan

A named entity recognition model fine-tuned based on XLM-RoBERTa large, supporting 10 high-resource languages, capable of identifying three types of entities: location, organization, and person.

Sequence Labeling

Transformers

#Multilingual NER #High-resource language support #News domain entity recognition

Downloads 5,173

Release Time : 3/2/2022

Model Overview

This model is a named entity recognition model for 10 high-resource languages, based on the fine-tuned XLM-RoBERTa large architecture, specifically designed to identify three types of entities in text: location (LOC), organization (ORG), and person (PER).

Model Features

Multilingual support

Supports named entity recognition in 10 high-resource languages, including non-Latin languages such as Arabic and Chinese.

Entity type recognition

Accurately identifies three main entity types: location (LOC), organization (ORG), and person (PER).

Based on XLM-RoBERTa

Fine-tuned based on the powerful XLM-RoBERTa large model, with excellent cross-language representation capabilities.

Model Capabilities

Multilingual text processing

Named entity recognition

Entity classification

Use Cases

Information extraction

News analysis

Extract information about people, organizations, and locations from multilingual news articles

Can construct knowledge graphs or perform event analysis

Document processing

Process entity information in multilingual documents

Facilitates document classification and information retrieval

Business intelligence

Market analysis

Extract company, product, and location information from multilingual market reports

Supports cross-border market trend analysis

🚀 xlm-roberta-large-ner-hrl

xlm-roberta-large-ner-hrl is a Named Entity Recognition model designed for 10 high-resourced languages, including Arabic, German, English, Spanish, French, Italian, Latvian, Dutch, Portuguese, and Chinese. It's based on a fine-tuned XLM-RoBERTa large model and can recognize three types of entities: location (LOC), organizations (ORG), and person (PER).

🚀 Quick Start

You can use this model with Transformers pipeline for NER.

from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("Davlan/xlm-roberta-large-ner-hrl")
model = AutoModelForTokenClassification.from_pretrained("Davlan/xlm-roberta-large-ner-hrl")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Nader Jokhadar had given Syria the lead with a well-struck header in the seventh minute."
ner_results = nlp(example)
print(ner_results)

✨ Features

Multilingual Support: Capable of performing NER on 10 high-resourced languages.
Entity Types: Trained to recognize three common types of entities: location, organizations, and person.

📚 Documentation

Model description

This model is a xlm-roberta-large model that was fine-tuned on an aggregation of 10 high-resourced languages.

Intended uses & limitations

How to use

As shown in the quick start section, you can use the model with Transformers pipeline for NER.

Limitations and bias

This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.

Training data

The training data for the 10 languages are from:

Property	Details
Arabic	ANERcorp
German	conll 2003
English	conll 2003
Spanish	conll 2002
French	Europeana Newspapers
Italian	Italian I-CAB
Latvian	Latvian NER
Dutch	conll 2002
Portuguese	Paramopama + Second Harem
Chinese	MSRA

The training dataset distinguishes between the beginning and continuation of an entity so that if there are back-to-back entities of the same type, the model can output where the second entity begins. As in the dataset, each token will be classified as one of the following classes:

Abbreviation	Description
O	Outside of a named entity
B-PER	Beginning of a person’s name right after another person’s name
I-PER	Person’s name
B-ORG	Beginning of an organisation right after another organisation
I-ORG	Organisation
B-LOC	Beginning of a location right after another location
I-LOC	Location

Training procedure

This model was trained on NVIDIA V100 GPU with recommended hyperparameters from HuggingFace code.

📄 License

This model is licensed under the afl-3.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご