Update README.md

README.md

@@ -21,7 +21,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mt5_summarize_japanese
 
-This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
+(Japanese caption : 日本語の要約のモデル)
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) trained for Japanese summarization.
+
+This model is trained on BBC news articles ([XL-Sum Japanese dataset](https://huggingface.co/datasets/csebuetnlp/xlsum/viewer/japanese)), in which the first sentence (headline sentence) is used for summary and others are used for articles.<br>
+So **please fill news story (including, such as, event, background, result, and comment) as source text in the inferece widget**. (Other corpra - such as, business document, book reading, or short tale - are not seen in training set.)
+
 It achieves the following results on the evaluation set:
 - Loss: 1.8952
 - Rouge1: 0.4625
@@ -29,20 +35,21 @@ It achieves the following results on the evaluation set:
 - Rougel: 0.3656
 - Rougelsum: 0.3868
 
-## Model description
-
-More information needed
+## Intended uses
 
-## Intended uses & limitations
+```python
+from transformers import pipeline
 
-More information needed
-
-## Training and evaluation data
-
-More information needed
+seq2seq = pipeline("summarization", model="tsmatz/mt5-summarize-jp")
+sample_text = "サッカーのワールドカップカタール大会、世界ランキング24位でグループEに属する日本は、23日の1次リーグ初戦において、世界11位で過去4回の優勝を誇るドイツと対戦しました。試合は前半、ドイツの一方的なペースではじまりましたが、後半、日本の森保監督は攻撃的な選手を積極的に動員して流れを変えました。結局、日本は前半に1点を奪われましたが、途中出場の堂安律選手と浅野拓磨選手が後半にゴールを決め、2対1で逆転勝ちしました。ゲームの流れをつかんだ森保采配が功を奏しました。"
+result = seq2seq(sample_text)
+print(result)
+```
 
 ## Training procedure
 
+You can download the source code for fine-tuning from [here](https://github.com/tsmatz/huggingface-finetune-japanese/blob/master/02-summarize.ipynb).
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: