commit files to HF hub

README.md

@@ -0,0 +1,135 @@
+
+---
+license: cc-by-4.0
+metrics:
+- bleu4
+- meteor
+- rouge-l
+- bertscore
+- moverscore
+language: zh
+datasets:
+- lmqg/qag_zhquad
+pipeline_tag: text2text-generation
+tags:
+- questions and answers generation
+widget:
+- text: "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。"
+  example_title: "Questions & Answers Generation Example 1" 
+model-index:
+- name: lmqg/mt5-base-zhquad-qag
+  results:
+  - task:
+      name: Text2text Generation
+      type: text2text-generation
+    dataset:
+      name: lmqg/qag_zhquad
+      type: default
+      args: default
+    metrics:
+    - name: QAAlignedF1Score-BERTScore (Question & Answer Generation)
+      type: qa_aligned_f1_score_bertscore_question_answer_generation
+      value: 73.57
+    - name: QAAlignedRecall-BERTScore (Question & Answer Generation)
+      type: qa_aligned_recall_bertscore_question_answer_generation
+      value: 74.12
+    - name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
+      type: qa_aligned_precision_bertscore_question_answer_generation
+      value: 73.07
+    - name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
+      type: qa_aligned_f1_score_moverscore_question_answer_generation
+      value: 49.76
+    - name: QAAlignedRecall-MoverScore (Question & Answer Generation)
+      type: qa_aligned_recall_moverscore_question_answer_generation
+      value: 49.92
+    - name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
+      type: qa_aligned_precision_moverscore_question_answer_generation
+      value: 49.62
+---
+
+# Model Card of `lmqg/mt5-base-zhquad-qag`
+This model is fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) for question & answer pair generation task on the [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
+
+
+### Overview
+- **Language model:** [google/mt5-base](https://huggingface.co/google/mt5-base)   
+- **Language:** zh  
+- **Training data:** [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) (default)
+- **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
+- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
+- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
+
+### Usage
+- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
+```python
+from lmqg import TransformersQG
+
+# initialize model
+model = TransformersQG(language="zh", model="lmqg/mt5-base-zhquad-qag")
+
+# model prediction
+question_answer_pairs = model.generate_qa("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`
+```python
+from transformers import pipeline
+
+pipe = pipeline("text2text-generation", "lmqg/mt5-base-zhquad-qag")
+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。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。")
+
+```
+
+## Evaluation
+
+
+- ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-base-zhquad-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_zhquad.default.json) 
+
+|                                 |   Score | Type    | Dataset                                                            |
+|:--------------------------------|--------:|:--------|:-------------------------------------------------------------------|
+| QAAlignedF1Score (BERTScore)    |   73.57 | default | [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) |
+| QAAlignedF1Score (MoverScore)   |   49.76 | default | [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) |
+| QAAlignedPrecision (BERTScore)  |   73.07 | default | [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) |
+| QAAlignedPrecision (MoverScore) |   49.62 | default | [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) |
+| QAAlignedRecall (BERTScore)     |   74.12 | default | [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) |
+| QAAlignedRecall (MoverScore)    |   49.92 | default | [lmqg/qag_zhquad](https://huggingface.co/datasets/lmqg/qag_zhquad) |
+
+
+
+## Training hyperparameters
+
+The following hyperparameters were used during fine-tuning:
+ - dataset_path: lmqg/qag_zhquad
+ - dataset_name: default
+ - input_types: ['paragraph']
+ - output_types: ['questions_answers']
+ - prefix_types: None
+ - model: google/mt5-base
+ - max_length: 512
+ - max_length_output: 256
+ - epoch: 4
+ - batch: 2
+ - lr: 0.001
+ - fp16: False
+ - random_seed: 1
+ - gradient_accumulation_steps: 32
+ - label_smoothing: 0.15
+
+The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-base-zhquad-qag/raw/main/trainer_config.json).
+
+## 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",
+}
+
+```

eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_zhquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.2077453790649394, "Bleu_2": 0.15669616212849166, "Bleu_3": 0.11329327069798292, "Bleu_4": 0.0675205628662687, "METEOR": 0.13149550299405027, "ROUGE_L": 0.2609240515597465, "BERTScore": 0.7150794306427541, "MoverScore": 0.49850276047443437, "QAAlignedF1Score (BERTScore)": 0.7350379663139712, "QAAlignedRecall (BERTScore)": 0.7253406724703527, "QAAlignedPrecision (BERTScore)": 0.7460203931739798, "QAAlignedF1Score (MoverScore)": 0.49478330796740533, "QAAlignedRecall (MoverScore)": 0.48941958475894903, "QAAlignedPrecision (MoverScore)": 0.5005154693716379}, "test": {"Bleu_1": 0.08653450389859453, "Bleu_2": 0.06361653603763276, "Bleu_3": 0.04326443681415462, "Bleu_4": 0.024136296807001266, "METEOR": 0.10530923349771895, "ROUGE_L": 0.19016124779262342, "BERTScore": 0.632117692622639, "MoverScore": 0.4921711252598822, "QAAlignedF1Score (BERTScore)": 0.7356638345459832, "QAAlignedRecall (BERTScore)": 0.7411721341960391, "QAAlignedPrecision (BERTScore)": 0.7307381935071808, "QAAlignedF1Score (MoverScore)": 0.4976474798290538, "QAAlignedRecall (MoverScore)": 0.4992147354755327, "QAAlignedPrecision (MoverScore)": 0.49618864901132487}}

trainer_config.json

@@ -0,0 +1 @@
+{"dataset_path": "lmqg/qag_zhquad", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": null, "model": "google/mt5-base", "max_length": 512, "max_length_output": 256, "epoch": 4, "batch": 2, "lr": 0.001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 32, "label_smoothing": 0.15}