句向量是指将语句映射至固定维度的实数向量。
将不定长的句子用定长的向量表示,为NLP下游任务提供服务。
支持 15 种语言:
Arabic, Chinese, Dutch, English, French, German, Italian, Korean, Polish, Portuguese, Russian, Spanish, Turkish.
句向量应用:
运行成功后,命令行应该看到下面的信息:
... # 测试语句: # 英文一组 [INFO ] - input Sentence1: This model generates embeddings for input sentence [INFO ] - input Sentence2: This model generates embeddings # 中文一组 [INFO ] - input Sentence3: 今天天气不错 [INFO ] - input Sentence4: 今天风和日丽 # 向量维度: [INFO ] - Vector dimensions: 512 # 英文 - 生成向量: [INFO ] - Sentence1 embeddings: [-0.07397884, 0.023079528, ..., -0.028247012, -0.08646198] [INFO ] - Sentence2 embeddings: [-0.084004365, -0.021871908, ..., -0.039803937, -0.090846084] #计算英文相似度: [INFO ] - 英文 Similarity: 0.77445346 # 中文 - 生成向量: [INFO ] - Sentence1 embeddings: [0.012180057, -0.035749275, ..., 0.0208446, -0.048238125] [INFO ] - Sentence2 embeddings: [0.016560446, -0.03528302, ..., 0.023508975, -0.046362665] #计算中文相似度: [INFO ] - 中文 Similarity: 0.9972926
http://www.aias.top/
https://github.com/mymagicpower/AIAS
https://gitee.com/mymagicpower/AIAS