pavlentiy/reviews-sentiment-multilingual-e5-base

Reviews Zero-Shot Sentiment Classification

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

import numpy as np
from sentence_transformers import SentenceTransformer, util

sentences = ["Замечательный препарат, все пользуемся", "Последнее время данный препарат вызывает у меня сыпь"]
classes = ['негатив', 'нейтрально', 'позитив']


model = SentenceTransformer('pavlentiy/reviews-sentiment-multilingual-e5-base')
embeddings = model.encode(sentences)
embeddings_classes = model.encode(classes)

# Compute cosine-similarities
cosine_scores = np.array(util.cos_sim(embeddings, embeddings_classes))

a = lambda t: {0:'негатив', 1:'нейтральная', 2:'позитив'}[t]
argmax = cosine_scores.argmax(axis=1)
result_classes = list(map(a, argmax))
print(result_classes)

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 802 with parameters:

{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss with parameters:

{'scale': 20.0, 'similarity_fct': 'cos_sim'}

Parameters of the fit()-Method:

{
    "epochs": 2,
    "evaluation_steps": 0,
    "evaluator": "sentence_transformers.evaluation.TranslationEvaluator.TranslationEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 160.4,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Citing & Authors