dataset: Add JapaneseSentimentClassification #2913
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR intends to add a Japanese dataset
JapaneseSentimentClassification
.We made this dataset based on
MultilingualSentimentClassification
. However, in the Japanese split ofMultilingualSentimentClassification
, sentences are splitted with spaces (that do not typically exist in natural Japanese texts) by morphological analysis tools. We found that the performances with/without spaces are totally different, so we reverted morphological analysis to remove unnatural spaces. Our method is not perfect but best-effort, as there're some corner cases in border of Japanese and non-Japanese words.We made it available in JMTEB, and here we cited JMTEB dataset.
mteb run -m {model_name} -t {task_name}
command.sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
intfloat/multilingual-e5-small
Here are some examples that show the difference between this dataset (
JapaneseSentimentClassification
) and the Japanese split of the originalMultilingualSentimentClassification
.JapaneseSentimentClassification
the Japanese split of MultilingualSentimentClassification
We tested several models to show that there is significant difference in whether spaces are removed.
evaluation script
test accuracy:
test f1: