Model Card of lmqg/mt5-small-zhquad-ae
This model is fine-tuned version of google/mt5-small for answer extraction on the lmqg/qg_zhquad (dataset_name: default) via lmqg
.
Overview
- Language model: google/mt5-small
- Language: en
- Training data: lmqg/qg_zhquad (default)
- Online Demo: https://autoqg.net/
- Repository: https://github.com/asahi417/lm-question-generation
- Paper: https://arxiv.org/abs/2210.03992
Usage
- With
lmqg
from lmqg import TransformersQG
# initialize model
model = TransformersQG(language="zh", model="lmqg/mt5-small-zhquad-ae")
# model prediction
answers = model.generate_a("南安普敦的警察服务由汉普郡警察提供。南安普敦行动的主要基地是一座新的八层专用建筑,造价3000万英镑。该建筑位于南路,2011年启用,靠近南安普敦中央火车站。此前,南安普顿市中心的行动位于市民中心西翼,但由于设施老化,加上计划在旧警察局和地方法院建造一座新博物馆,因此必须搬迁。在Portswood、Banister Park、Hille和Shirley还有其他警察局,在南安普顿中央火车站还有一个英国交通警察局。")
- With
transformers
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mt5-small-zhquad-ae")
output = pipe('南安普敦的警察服务由汉普郡警察提供。 南安普敦行动的主要基地是一座新的八层专用建筑,造价3000万英镑。 <hl> 该建筑位于南路,2011年启用,靠近 南安普敦中央 火车站。 <hl> 此前,南安普顿市中心的行动位于市民中心西翼,但由于设施老化,加上计划在旧警察局和地方法院建造一座新博物馆,因此必须搬迁。 在Portswood、Banister Park、Hille和Shirley还有其他警察局,在南安普顿中央火车站还有一个英国交通警察局。')
Evaluation
- Metric (Answer Extraction): raw metric file
Score | Type | Dataset | |
---|---|---|---|
AnswerExactMatch | 95.08 | default | lmqg/qg_zhquad |
AnswerF1Score | 95.17 | default | lmqg/qg_zhquad |
BERTScore | 99.78 | default | lmqg/qg_zhquad |
Bleu_1 | 92.07 | default | lmqg/qg_zhquad |
Bleu_2 | 88.98 | default | lmqg/qg_zhquad |
Bleu_3 | 85.68 | default | lmqg/qg_zhquad |
Bleu_4 | 82.12 | default | lmqg/qg_zhquad |
METEOR | 70.98 | default | lmqg/qg_zhquad |
MoverScore | 98.8 | default | lmqg/qg_zhquad |
ROUGE_L | 95.7 | default | lmqg/qg_zhquad |
Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_zhquad
- dataset_name: default
- input_types: ['paragraph_sentence']
- output_types: ['answer']
- prefix_types: None
- model: google/mt5-small
- max_length: 512
- max_length_output: 32
- epoch: 4
- batch: 16
- lr: 0.0005
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 4
- label_smoothing: 0.15
The full configuration can be found at fine-tuning config file.
Citation
@inproceedings{ushio-etal-2022-generative,
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
author = "Ushio, Asahi and
Alva-Manchego, Fernando and
Camacho-Collados, Jose",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, U.A.E.",
publisher = "Association for Computational Linguistics",
}
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Dataset used to train lmqg/mt5-small-zhquad-ae
Evaluation results
- BLEU4 (Answer Extraction) on lmqg/qg_zhquadself-reported82.120
- ROUGE-L (Answer Extraction) on lmqg/qg_zhquadself-reported95.700
- METEOR (Answer Extraction) on lmqg/qg_zhquadself-reported70.980
- BERTScore (Answer Extraction) on lmqg/qg_zhquadself-reported99.780
- MoverScore (Answer Extraction) on lmqg/qg_zhquadself-reported98.800
- AnswerF1Score (Answer Extraction) on lmqg/qg_zhquadself-reported95.170
- AnswerExactMatch (Answer Extraction) on lmqg/qg_zhquadself-reported95.080