Downloads · 30 days
9
3% of all-time downloads
Toshifumi/001_M-BERT-claim-classifier
001_M-BERT-claim-classifier is a text classification model from Toshifumi. Use it when you need a label for a piece of text. It is set up for transformers.
probably proofread and complete it, then remove this comment. --
Downloads · 30 days
9
3% of all-time downloads
All-time downloads
313
Public
Repo size
712 MB
Likes
0
Public
Click a slice to open those files.
.h5712 MB · 99%
From the Hugging Face model README
このモデルは、当該クレームがどのプロダクトについてのものかを判別します。右側の"Hosted inference API" 直下のBOXにお好きなクレームを入力し、"Compute"ボタンをクリックして下さい。30〜60秒前後で答えが返ってきます。答えは以下の5つのlabelのいずれかです。 入力は最大300〜400文字、日本語・英語他100カ国語以上に対応してます。教育用ですので、機密情報は入力しないで下さい。
「私の夫と私はローンデポを通じてローンのRefiローンを申請し、その後承認されました。私たちはそれが次週になると言われているプロセスで前進することにしました。 両当事者と鑑定評価で実行されました。私たちの料金は次の週に有効であることが開示されました。貸出金の担当者によって連絡しました。ローンが45日以内に閉じなかった場合、当社の元のレートオファーが拡張されます。ロックレートが期限切れになったことを示すXXXXから別のコミュニケーション(Eメール)を受け取り、新しい料金を取得する必要があります。」
This model determines which product the claim is about. Enter your favorite claim in the box directly under "Hosted inference API" on the right, and click the "Compute" button. You will receive an answer within 30-60 seconds. The answer is one of the following five labels. You can enter a maximum of 400 to 500 characters, and it supports Japanese, English, and more than 100 languages.
This is for educational purposes only, please do not enter confidential information.
I drew an advance of $2900.00 from my HELOC that I have with Wells Fargo. I have auto pay with Wells Fargo and a scheduled payment of $100.00 was taken from mychecking ac. I entered the bank, CA branch and paid $2800.00 to pay off the advance. Since that time, various transactions have been posted to this account. There is a principal adj debit in the amount of $170.00 followed by a principal reversal in the amount of $91.
It achieves the following results on the evaluation set:
bert-base-multilingual-cased
This is solely for educational purposes. This cannot be used for investments or businesses in practice. I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithm or ideas contained herein, or acting or refraining from acting as a result of such use. I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on me to correct any errors or defects in the codes and the software.
The following hyperparameters were used during training: