--- pipeline_tag: sentence-similarity tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers --- # KBLab/sentence-bert-swedish-cased This is a [sentence-transformers](https://www.SBERT.net) model: It maps Swedish sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. This model is a bilingual Swedish-English model trained according to instructions in the paper [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://arxiv.org/pdf/2004.09813.pdf) and the [documentation](https://www.sbert.net/examples/training/multilingual/README.html) accompanying its companion python package. We have used the strongest available pretrained English Bi-Encoder ([paraphrase-mpnet-base-v2](https://www.sbert.net/docs/pretrained_models.html#sentence-embedding-models)) as a teacher model, and the pretrained Swedish [KB-BERT](https://huggingface.co/KB/bert-base-swedish-cased) as the student model. ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('KBLab/sentence-bert-swedish-cased') embeddings = model.encode(sentences) print(embeddings) ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), 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. ```python 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 = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # 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, max pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results The model was evaluated on [SweParaphrase v1.0](https://spraakbanken.gu.se/en/resources/sweparaphrase) by calculating Pearson and Spearman correlation between predicted model similarity scores and the human similarity score labels. The model achieved a Pearson correlation coefficient of **0.918** and a Spearman's rank correlation coefficient of **0.911**. The following code snippet can be used to reproduce the above results: ```python from sentence_transformers import SentenceTransformer import pandas as pd df = pd.read_csv( "sweparaphrase-dev-165.csv", sep="\t", header=None, names=[ "original_id", "source", "type", "sentence_swe1", "sentence_swe2", "score", "sentence1", "sentence2", ], ) model = SentenceTransformer("KBLab/sentence-bert-swedish-cased") sentences1 = df["sentence_swe1"].tolist() sentences2 = df["sentence_swe2"].tolist() # Compute embedding for both lists embeddings1 = model.encode(sentences1, convert_to_tensor=True) embeddings2 = model.encode(sentences2, convert_to_tensor=True) # Compute cosine similarity after normalizing embeddings1 /= embeddings1.norm(dim=-1, keepdim=True) embeddings2 /= embeddings2.norm(dim=-1, keepdim=True) cosine_scores = embeddings1 @ embeddings2.t() sentence_pair_scores = cosine_scores.diag() df["model_score"] = sentence_pair_scores.cpu().tolist() print(df[["score", "model_score"]].corr(method="spearman")) print(df[["score", "model_score"]].corr(method="pearson")) ``` ## Training Around 14.6 million sentences from English-Swedish parallel corpuses were used to train the model. Data was sourced from the [Open Parallel Corpus](https://opus.nlpl.eu/) (OPUS) and downloaded via the python package [opustools](https://pypi.org/project/opustools/). Datasets used were: JW300, EUbooks, Europarl, EUbookshop, EMEA, TED2020, Tatoeba and OpenSubtitles. The model was trained with the parameters: **DataLoader**: `torch.utils.data.dataloader.DataLoader` of length 227832 with parameters: ``` {'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` **Loss**: `sentence_transformers.losses.MSELoss.MSELoss` Parameters of the fit()-Method: ``` { "callback": null, "epochs": 7, "evaluation_steps": 1000, "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator", "max_grad_norm": 1, "optimizer_class": "", "optimizer_params": { "correct_bias": false, "eps": 1e-06, "lr": 2e-05 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 10000, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 256, '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}) ) ``` ## Citing & Authors This model was trained by KBLab, a data lab at the National Library of Sweden. ## Acknowledgements We gratefully acknowledge the HPC RIVR consortium (www.hpc-rivr.si) and EuroHPC JU (eurohpc-ju.europa.eu) for funding this research by providing computing resources of the HPC system Vega at the Institute of Information Science (www.izum.si).