license: apache-2.0
Model Card for luke-large-finetuned-conll-2003
Model Details
Model Description
LUKE (Language Understanding with Knowledge-based Embeddings) is a new pretrained contextualized representation of words and entities based on transformer.
- Developed by: Studio Ousia
- Shared by [Optional]: More information needed
- Model type: EntitySpanClassification
- Language(s) (NLP): More information needed
- License: Apache-2.0
- Related Models: Luke-large
- Parent Model: Luke
- Resources for more information:
Uses
Direct Use
More information needed
Downstream Use [Optional]
This model can also be used for the task of named entity recognition, cloze-style question answering, fine-grained entity typing, extractive question answering.
Out-of-Scope Use
The model should not be used to intentionally create hostile or alienating environments for people.
Bias, Risks, and Limitations
Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
Training Details
Training Data
More information needed
Training Procedure
Preprocessing
More information needed
Speeds, Sizes, Times
More information needed
Evaluation
Testing Data, Factors & Metrics
Testing Data
More information needed
Factors
Metrics
LUKE achieves state-of-the-art results on five popular NLP benchmarks including
- SQuAD v1.1 (extractive question answering),
- CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering),
- TACRED (relation classification), and
- Open Entity (entity typing).
Results
The experimental results are provided as follows:
| Task | Dataset | Metric | LUKE-large | luke-base | Previous SOTA |
|---|---|---|---|---|---|
| Extractive Question Answering | SQuAD v1.1 | EM/F1 | 90.2/95.4 | 86.1/92.3 | 89.9/95.1 (Yang et al., 2019) |
| Named Entity Recognition | CoNLL-2003 | F1 | 94.3 | 93.3 | 93.5 (Baevski et al., 2019) |
| Cloze-style Question Answering | ReCoRD | EM/F1 | 90.6/91.2 | - | 83.1/83.7 (Li et al., 2019) |
| Relation Classification | TACRED | F1 | 72.7 | - | 72.0 (Wang et al. , 2020) |
| Fine-grained Entity Typing | Open Entity | F1 | 78.2 | - | 77.6 (Wang et al. , 2020) |
Please check the Github repository for more details and updates.
Model Examination
More information needed
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: More information needed
- Hours used: More information needed
- Cloud Provider: More information needed
- Compute Region: More information needed
- Carbon Emitted: More information needed
Technical Specifications [optional]
Model Architecture and Objective
More information needed
Compute Infrastructure
More information needed
Hardware
- transformers_version: 4.6.0.dev0
Software
More information needed
Citation
BibTeX:
@inproceedings{yamada2020luke,
title={LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention},
author={Ikuya Yamada and Akari Asai and Hiroyuki Shindo and Hideaki Takeda and Yuji Matsumoto},
booktitle={EMNLP},
year={2020}
}
Glossary [optional]
More information needed
More Information [optional]
More information needed
Model Card Authors [optional]
Studio Ousia in collaboration with Ezi Ozoani and the Hugging Face team
Model Card Contact
More information needed
How to Get Started with the Model
Use the code below to get started with the model.
Click to expand
from transformers import AutoTokenizer, LukeForEntitySpanClassification
tokenizer = AutoTokenizer.from_pretrained("studio-ousia/luke-large-finetuned-conll-2003")
model = LukeForEntitySpanClassification.from_pretrained("studio-ousia/luke-large-finetuned-conll-2003")