README.md

metadata

pipeline_tag: sentence-similarity
license: apache-2.0
tags:
  - text2vec
  - feature-extraction
  - sentence-similarity
  - transformers
datasets:
  - shibing624/nli_zh
language:
  - zh
metrics:
  - bleu
library_name: transformers

shibing624/text2vec-base-chinese-sentence

This is a CoSENT(Cosine Sentence) model: shibing624/text2vec-base-chinese-sentence.

It maps sentences to a 768 dimensional dense vector space and can be used for tasks like sentence embeddings, text matching or semantic search.

• using all 5 tasks' datasets, dataset: https://huggingface.co/datasets/shibing624/nli_zh
• base model: nghuyong/ernie-3.0-base-zh
• max_seq_length = 256
• best epoch: 2

Evaluation

For an automated evaluation of this model, see the Evaluation Benchmark: text2vec

• 本项目release模型的中文匹配评测结果：

Arch	BaseModel	Model	ATEC	BQ	LCQMC	PAWSX	STS-B	Avg	QPS
Word2Vec	word2vec	w2v-light-tencent-chinese	20.00	31.49	59.46	2.57	55.78	33.86	23769
SBERT	xlm-roberta-base	sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2	18.42	38.52	63.96	10.14	78.90	41.99	3138
CoSENT	hfl/chinese-macbert-base	shibing624/text2vec-base-chinese	31.93	42.67	70.16	17.21	79.30	48.25	3008
CoSENT	hfl/chinese-lert-large	GanymedeNil/text2vec-large-chinese	32.61	44.59	69.30	14.51	79.44	48.08	2092
CoSENT	nghuyong/ernie-3.0-base-zh	shibing624/text2vec-base-chinese-sentence	51.26	68.72	79.13	34.28	80.70	62.81	3066

Usage (text2vec)

Using this model becomes easy when you have text2vec installed:

pip install -U text2vec

Then you can use the model like this:

from text2vec import SentenceModel
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']

model = SentenceModel('shibing624/text2vec-base-chinese-sentence')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without text2vec, you can use the model like this:

First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

Install transformers:

pip install transformers

Then load model and predict:

from transformers import BertTokenizer, BertModel
import torch

# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]  # First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

# Load model from HuggingFace Hub
tokenizer = BertTokenizer.from_pretrained('shibing624/text2vec-base-chinese-sentence')
model = BertModel.from_pretrained('shibing624/text2vec-base-chinese-sentence')
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)

Usage (sentence-transformers)

sentence-transformers is a popular library to compute dense vector representations for sentences.

Install sentence-transformers:

pip install -U sentence-transformers

Then load model and predict:

from sentence_transformers import SentenceTransformer

m = SentenceTransformer("shibing624/text2vec-base-chinese-sentence")
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']

sentence_embeddings = m.encode(sentences)
print("Sentence embeddings:")
print(sentence_embeddings)

Full Model Architecture

CoSENT(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_mean_tokens': True})
)

Citing & Authors

This model was trained by text2vec.

If you find this model helpful, feel free to cite:

@software{text2vec,
  author = {Ming Xu},
  title = {text2vec: A Tool for Text to Vector},
  year = {2023},
  url = {https://github.com/shibing624/text2vec},
}