Downloads · 30 days
11
2% of all-time downloads
vocabtrimmer/mbart-large-cc25-trimmed-ko-koquad-qg
mbart-large-cc25-trimmed-ko-koquad-qg is a text generation model from vocabtrimmer. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-4.0.
This model is fine-tuned version of vocabtrimmer/mbart-large-cc25-trimmed-ko for question generation task on the lmqg/qgkoquad (datasetname: default) via lmqg.
Downloads · 30 days
11
2% of all-time downloads
All-time downloads
481
Public
Repo size
3.2 GB
Likes
0
Public
Click a slice to open those files.
.bin1.6 GB · 99%
From the Hugging Face model README
vocabtrimmer/mbart-large-cc25-trimmed-ko-koquad-qgThis model is fine-tuned version of vocabtrimmer/mbart-large-cc25-trimmed-ko for question generation task on the lmqg/qg_koquad (dataset_name: default) via lmqg.
lmqgfrom lmqg import TransformersQG
# initialize model
model = TransformersQG(language="ko", model="vocabtrimmer/mbart-large-cc25-trimmed-ko-koquad-qg")
# model prediction
questions = model.generate_q(list_context="1990년 영화 《 남부군 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.", list_answer="남부군")
transformersfrom transformers import pipeline
pipe = pipeline("text2text-generation", "vocabtrimmer/mbart-large-cc25-trimmed-ko-koquad-qg")
output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영화배우 첫 데뷔에 이어 같은 해 KBS 드라마 《지구인》에서 단역으로 출연하였고 이듬해 MBC 《여명의 눈동자》를 통해 단역으로 출연하였다.")
| Score | Type | Dataset | |
|---|---|---|---|
| BERTScore | 83.8 | default | lmqg/qg_koquad |
| Bleu_1 | 27.01 | default | lmqg/qg_koquad |
| Bleu_2 | 19.9 | default | lmqg/qg_koquad |
| Bleu_3 | 15.07 | default | lmqg/qg_koquad |
| Bleu_4 | 11.59 | default | lmqg/qg_koquad |
| METEOR | 30.17 | default | lmqg/qg_koquad |
| MoverScore | 82.98 | default | lmqg/qg_koquad |
| ROUGE_L | 27.96 | default | lmqg/qg_koquad |
The following hyperparameters were used during fine-tuning:
The full configuration can be found at fine-tuning config file.
@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",
}