model update

README.md

@@ -29,61 +29,42 @@ model-index:
     metrics:
     - name: BLEU4
       type: bleu4
-      value: 0.12931835496445465
+      value: 12.93
     - name: ROUGE-L
       type: rouge-l
-      value: 0.36535644337488943
+      value: 36.54
     - name: METEOR
       type: meteor
-      value: 0.30354623890919497
+      value: 30.35
     - name: BERTScore
       type: bertscore
-      value: 0.9055079668504705
+      value: 90.55
     - name: MoverScore
       type: moverscore
-      value: 0.6182219856624396
+      value: 61.82
     - name: QAAlignedF1Score (BERTScore)
       type: qa_aligned_f1_score_bertscore
-      value: 0.9237100142709498
+      value: 92.37
     - name: QAAlignedRecall (BERTScore)
       type: qa_aligned_recall_bertscore
-      value: 0.9200981234774854
+      value: 92.01
     - name: QAAlignedPrecision (BERTScore)
       type: qa_aligned_precision_bertscore
-      value: 0.92746748296856
+      value: 92.75
     - name: QAAlignedF1Score (MoverScore)
       type: qa_aligned_f1_score_moverscore
-      value: 0.646258531258488
+      value: 64.63
     - name: QAAlignedRecall (MoverScore)
       type: qa_aligned_recall_moverscore
-      value: 0.6385009999155912
+      value: 63.85
     - name: QAAlignedPrecision (MoverScore)
       type: qa_aligned_precision_moverscore
-      value: 0.655031044484246
+      value: 65.5
 ---
 
 # Model Card of `lmqg/t5-base-tweetqa-qag`
-This model is fine-tuned version of [t5-base](https://huggingface.co/t5-base) for question generation task on the 
-[lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
-This model is fine-tuned on the end-to-end question and answer generation.
+This model is fine-tuned version of [t5-base](https://huggingface.co/t5-base) for question & answer pair generation task on the [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
 
-Please cite our paper if you use the model ([https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)).
-
-```
-
-@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",
-}
-
-```
 
 ### Overview
 - **Language model:** [t5-base](https://huggingface.co/t5-base)   
@@ -96,42 +77,46 @@ Please cite our paper if you use the model ([https://arxiv.org/abs/2210.03992](h
 ### 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='en', model='lmqg/t5-base-tweetqa-qag')
+model = TransformersQG(language="en", model="lmqg/t5-base-tweetqa-qag")
+
 # model prediction
-question = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")
-        
+question_answer_pairs = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")
+
 ```
 
 - With `transformers`
 ```python
-
 from transformers import pipeline
-# initialize model
-pipe = pipeline("text2text-generation", 'lmqg/t5-base-tweetqa-qag')
-# question generation
-question = pipe('generate question and answer: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')
-
-```
-
-## Evaluation Metrics
 
+pipe = pipeline("text2text-generation", "lmqg/t5-base-tweetqa-qag")
+output = pipe("generate question and answer: Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
 
-### Metrics
-
-| Dataset | Type | BLEU4 | ROUGE-L | METEOR | BERTScore | MoverScore | Link |
-|:--------|:-----|------:|--------:|-------:|----------:|-----------:|-----:|
-| [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.129 | 0.365 | 0.304 | 0.906 | 0.618 | [link](https://huggingface.co/lmqg/t5-base-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
+```
 
+## Evaluation
 
-### Metrics (QAG)
 
-| Dataset | Type | QA Aligned F1 Score (BERTScore) | QA Aligned F1 Score (MoverScore) | Link |
-|:--------|:-----|--------------------------------:|---------------------------------:|-----:|
-| [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) | default | 0.924 | 0.646 | [link](https://huggingface.co/lmqg/t5-base-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) | 
+- ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/t5-base-tweetqa-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_tweetqa.default.json) 
 
+|                                 |   Score | Type    | Dataset                                                              |
+|:--------------------------------|--------:|:--------|:---------------------------------------------------------------------|
+| BERTScore                       |   90.55 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| Bleu_1                          |   39.29 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| Bleu_2                          |   26.69 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| Bleu_3                          |   18.4  | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| Bleu_4                          |   12.93 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| METEOR                          |   30.35 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| MoverScore                      |   61.82 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| QAAlignedF1Score (BERTScore)    |   92.37 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| QAAlignedF1Score (MoverScore)   |   64.63 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| QAAlignedPrecision (BERTScore)  |   92.75 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| QAAlignedPrecision (MoverScore) |   65.5  | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| QAAlignedRecall (BERTScore)     |   92.01 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| QAAlignedRecall (MoverScore)    |   63.85 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
+| ROUGE_L                         |   36.54 | default | [lmqg/qag_tweetqa](https://huggingface.co/datasets/lmqg/qag_tweetqa) |
 
 
 
@@ -158,7 +143,6 @@ The full configuration can be found at [fine-tuning config file](https://hugging
 
 ## 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