cardiffnlp
/
twitter-xlm-roberta-base-sentiment
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' of https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment into main

This commit is contained in:
cardiffnlp 2021-04-17 05:57:04 +00:00
parent 891655a348 199ac16fae
commit 1f8684fe27
1 changed files with 10 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
README.md
View File

@ -1,19 +1,9 @@
# twitter-XLM-roBERTa-base for Sentiment Analysis # twitter-XLM-roBERTa-base for Sentiment Analysis
This is a XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis in
- Paper: [XLM-T: A Multilingual Language Model Toolkit for Twitter](https://...).
TODO: create model card - Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/xlm-t).
This is a roBERTa-base model trained on ~58M tweets and finetuned for sentiment analysis with the TweetEval benchmark.
- Paper: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf).
- Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval).
## Example of classification ## Example of classification
@ -37,22 +27,17 @@ def preprocess(text):
new_text.append(t) new_text.append(t)
return " ".join(new_text) return " ".join(new_text)
# Tasks:
# emoji, emotion, hate, irony, offensive, sentiment
# stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary
task='sentiment'
MODEL = f"cardiffnlp/twitter-roberta-base-{task}"
MODEL = f"cardiffnlp/twitter-xlm-roberta-base-sentiment"
tokenizer = AutoTokenizer.from_pretrained(MODEL) tokenizer = AutoTokenizer.from_pretrained(MODEL)
# download label mapping # download label mapping
labels=[] labels=[]
mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt" mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/sentiment/mapping.txt"
with urllib.request.urlopen(mapping_link) as f: with urllib.request.urlopen(mapping_link) as f:
html = f.read().decode('utf-8').split("\ html = f.read().decode('utf-8').split("\\
") ")
csvreader = csv.reader(html, delimiter='\\t') csvreader = csv.reader(html, delimiter='\\\\t')
labels = [row[1] for row in csvreader if len(row) > 1] labels = [row[1] for row in csvreader if len(row) > 1]
# PT # PT
@ -88,8 +73,8 @@ for i in range(scores.shape[0]):
Output: Output:
``` ```
1) positive 0.8466 1) positive 0.76726073
2) neutral 0.1458 2) neutral 0.201
3) negative 0.0076 3) negative 0.0312
``` ```