|
--- |
|
license: cc-by-sa-3.0 |
|
language: |
|
- ja |
|
base_model: |
|
- tohoku-nlp/bert-base-japanese-whole-word-masking |
|
metrics: |
|
- accuracy |
|
pipeline_tag: text-classification |
|
library_name: transformers |
|
tags: |
|
- japanese |
|
- emotion |
|
- emotion-classification |
|
--- |
|
# txt2emovec |
|
## 概要 |
|
txt2emovec (txt to emotion vector)<br> |
|
ユーザー入力を一度ずつtxt2emovecに食わせて8要素(喜び, 悲しみ, 期待, 驚き, 怒り, 恐怖, 嫌悪, 信頼)のベクトルに変換するためのモデル<br> |
|
talknizer: [tohoku-nlp/bert-base-japanese-whole-word-masking](https://huggingface.co/tohoku-nlp/bert-base-japanese-whole-word-masking)<br> |
|
dataset: [ids-cv/wrime](https://github.com/ids-cv/wrime) の[wrime-ver1.tsv](https://github.com/ids-cv/wrime/blob/master/wrime-ver1.tsv) |
|
|
|
## version |
|
v0.0: 2024/11/13: データセットがwrime-v1のみということもあり、データに偏りがあるようで、予測精度もそれなり |
