Debatenet 2 Cat

🚀 nblokker/debatenet-2-cat

このモデルはsentence-transformersモデルです。文章や段落を768次元の密ベクトル空間にマッピングし、クラスタリングや意味検索などのタスクに使用できます。

このモデルは、移民関連の要求や提案を含む文章間の類似度を推定するために使用できます。詳細と潜在的な使用例については、このブログ記事を参照してください。

🚀 クイックスタート

このモデルは、sentence-transformersをインストールすることで簡単に使用できます。

pip install -U sentence-transformers

その後、以下のようにモデルを使用できます。

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('nblokker/debatenet-2-cat')
embeddings = model.encode(sentences)
print(embeddings)

✨ 主な機能

• 文章や段落を768次元の密ベクトル空間にマッピングする。
• クラスタリングや意味検索などのタスクに使用できる。
• 移民関連の要求や提案を含む文章間の類似度を推定できる。

📦 インストール

sentence-transformersを使用する場合

pip install -U sentence-transformers

sentence-transformersを使用しない場合

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('nblokker/debatenet-2-cat')
model = AutoModel.from_pretrained('nblokker/debatenet-2-cat')

# 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)

💻 使用例

基本的な使用法

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('nblokker/debatenet-2-cat')
embeddings = model.encode(sentences)
print(embeddings)

高度な使用法

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('nblokker/debatenet-2-cat')
model = AutoModel.from_pretrained('nblokker/debatenet-2-cat')

# 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)

📚 ドキュメント

評価結果

このモデルの自動評価については、Sentence Embeddings Benchmarkを参照してください。https://seb.sbert.net

学習

このモデルは以下のパラメータで学習されました。

DataLoader:

{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

sentence_transformers.losses.BatchHardSoftMarginTripletLoss.BatchHardSoftMarginTripletLoss

fit()メソッドのパラメータ:

{
    "epochs": 15,
    "evaluation_steps": 120.5,
    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 120.5,
    "weight_decay": 0.01
}

モデルの完全なアーキテクチャ

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, '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})
)

引用と著者

@preprint{blokker2023,
  author = {Blokker, Nico and Blessing, Andre and Dayanik, Erenay and Kuhn, Jonas and Padó, Sebastian and Lapesa, Gabriella},
  note = {To appear in \textit{Language Resources and Evaluation}},
  title = {Between welcome culture and border fence: The {E}uropean refugee crisis in {G}erman newspaper reports},
  url = {https://arxiv.org/abs/2111.10142},
  year = 2023
}

@inproceedings{lapesa2020,
  abstract = {DEbateNet-migr15 is a manually annotated dataset for German which covers the public debate on immigration in 2015. The building block of our annotation is the political science notion of a claim, i.e., a statement made by a political actor (a politician, a party, or a group of citizens) that a specific action should be taken (e.g., vacant flats should be assigned to refugees). We identify claims in newspaper articles, assign them to actors and fine-grained categories and annotate their polarity and date. The aim of this paper is two-fold: first, we release the full DEbateNet-mig15 corpus and document it by means of a quantitative and qualitative analysis; second, we demonstrate its application in a discourse network analysis framework, which enables us to capture the temporal dynamics of the political debate.},
  address = {Online},
  author = {Lapesa, Gabriella and Blessing, Andre and Blokker, Nico and Dayanik, Erenay and Haunss, Sebastian and Kuhn, Jonas and Padó, Sebastian},
  booktitle = {Proceedings of LREC},
  pages = {919--927},
  title = {{DEbateNet-mig15}: {T}racing the 2015 Immigration Debate in {G}ermany Over Time},
  url = {https://www.aclweb.org/anthology/2020.lrec-1.115},
  year = 2020
}

謝辞

このモデルは、sentence-transformers/paraphrase-multilingual-mpnet-base-v2モデルをベースにしています。

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}

• オリジナルモデルのURL: https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2
• ライセンス: Apache 2.0

📄 ライセンス

このモデルの微調整部分はMITライセンスの下で公開されています。詳細については、LICENSEファイルを参照してください。オリジナルのsentence-transformers/paraphrase-multilingual-mpnet-base-v2モデルは、元のApache 2.0ライセンスのままです。

情報テーブル