模型:

TurkuNLP/sbert-cased-finnish-paraphrase

英文

字段名未翻译

从FinBERT训练的芬兰语BERT模型。可以在4亿个句子的数据集中找到相似度最高的句子的演示 here

训练

  • 图书馆: sentence-transformers
  • FinBERT模型:TurkuNLP/bert-base-finnish-cased-v1
  • 数据:提供的数据 here ,包括芬兰语释义语料库和自动收集的释义候选(500K个正例和5M个负例)
  • 汇集:均值汇集
  • 任务:二进制预测,两个句子是否是释义。注意:标签3和4被认为是释义,标签1和2是非释义。 Details on labels

使用

与HuggingFace文档中的 the English Sentence Transformer 相同。可以通过SentenceTransformer或HuggingFace Transformers进行。

SentenceTransformer

from sentence_transformers import SentenceTransformer
sentences = ["Tämä on esimerkkilause.", "Tämä on toinen lause."]

model = SentenceTransformer('TurkuNLP/sbert-cased-finnish-paraphrase')
embeddings = model.encode(sentences)
print(embeddings)

HuggingFace Transformers

from transformers import AutoTokenizer, AutoModel
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)


# Sentences we want sentence embeddings for
sentences = ["Tämä on esimerkkilause.", "Tämä on toinen lause."]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('TurkuNLP/sbert-cased-finnish-paraphrase')
model = AutoModel.from_pretrained('TurkuNLP/sbert-cased-finnish-paraphrase')

# 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)

评估结果

目前正在起草详细的评估结果的出版物。

完整的模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

引用和作者

在出版物起草中,请引用 this page

参考文献

  • J. Kanerva, F. Ginter, LH. Chang, I. Rastas, V. Skantsi, J. Kilpeläinen, HM. Kupari, J. Saarni, M. Sevón, and O. Tarkka. Finnish Paraphrase Corpus. 在NoDaLiDa 2021,2021中。
  • N. Reimers和I. Gurevych。 Sentence-BERT:使用Siamese BERT网络的句子嵌入。 在EMNLP-IJCNLP中,页3982-3992,2019。
  • A. Virtanen,J. Kanerva,R. Ilo,J. Luoma,J. Luotolahti,T. Salakoski,F. Ginter和S. Pyysalo。多语言不足够:用于芬兰语的BERT。 arXiv预印本arXiv:1912.07076,2019。