{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibxyg7xoa3brnksawwk372ztjce4fs5ydhovkzmql6ef5fgdqosem",
"uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mjjyqndwmvo2"
},
"path": "/t/why-this-bertscore-has-a-high-precision/175276#post_1",
"publishedAt": "2026-04-15T12:51:02.000Z",
"site": "https://discuss.huggingface.co",
"textContent": "Hello everyone, I’ve been studying transformer lately and I confused with BERTScore. So I tried to check the score of “who are you” and “look at the dogs” but I dont understand why the precision is really high? its preicions is 86% or am I doing it wrong?\n\nHere is my code\n\n\n bert_metric.compute(\n predictions=[\"who are you\"],\n references=[[\"look at the dogs\"]],\n lang='en'\n )\n\n\n\n\n\nand here is the output\n`{‘precision’: [0.8612378835678101],`\n`‘recall’: [0.8896267414093018],`\n`‘f1’: [0.8752021789550781],`\n`‘hashcode’: ‘roberta-large_L17_no-idf_version=0.3.12(hug_trans=5.0.0)’}`\n\nThanks in advance!",
"title": "Why this BERTScore has a high precision?"
}