🚀 抽象文書記述マッピングモデル
このモデルは、抽象的な文の記述を、その記述に適合する文にマッピングするためのものです。Wikipediaのデータを使って学習されています。load_finetuned_model
を使ってクエリエンコーダと文エンコーダを読み込み、encode_batch()
を使って文をエンコードすることができます。
🚀 クイックスタート
このモデルは、抽象的な文の記述を、その記述に適合する文にマッピングするために使用されます。Wikipediaのデータで学習されています。
✨ 主な機能
- 抽象的な文の記述を、その記述に適合する文にマッピングする。
- Wikipediaのデータで学習されている。
💻 使用例
基本的な使用法
from transformers import AutoTokenizer, AutoModel
import torch
from typing import List
from sklearn.metrics.pairwise import cosine_similarity
def load_finetuned_model():
sentence_encoder = AutoModel.from_pretrained("biu-nlp/abstract-sim-sentence")
query_encoder = AutoModel.from_pretrained("biu-nlp/abstract-sim-query")
tokenizer = AutoTokenizer.from_pretrained("biu-nlp/abstract-sim-sentence")
return tokenizer, query_encoder, sentence_encoder
def encode_batch(model, tokenizer, sentences: List[str], device: str):
input_ids = tokenizer(sentences, padding=True, max_length=512, truncation=True, return_tensors="pt",
add_special_tokens=True).to(device)
features = model(**input_ids)[0]
features = torch.sum(features[:,1:,:] * input_ids["attention_mask"][:,1:].unsqueeze(-1), dim=1) / torch.clamp(torch.sum(input_ids["attention_mask"][:,1:], dim=1, keepdims=True), min=1e-9)
return features
高度な使用法
tokenizer, query_encoder, sentence_encoder = load_finetuned_model()
relevant_sentences = ["Fingersoft's parent company is the Finger Group.",
"WHIRC – a subsidiary company of Wright-Hennepin",
"CK Life Sciences International (Holdings) Inc. (), or CK Life Sciences, is a subsidiary of CK Hutchison Holdings",
"EM Microelectronic-Marin (subsidiary of The Swatch Group).",
"The company is currently a division of the corporate group Jam Industries.",
"Volt Technical Resources is a business unit of Volt Workforce Solutions, a subsidiary of Volt Information Sciences (currently trading over-the-counter as VISI.)."
]
irrelevant_sentences = ["The second company is deemed to be a subsidiary of the parent company.",
"The company has gone through more than one incarnation.",
"The company is owned by its employees.",
"Larger companies compete for market share by acquiring smaller companies that may own a particular market sector.",
"A parent company is a company that owns 51% or more voting stock in another firm (or subsidiary).",
"It is a holding company that provides services through its subsidiaries in the following areas: oil and gas, industrial and infrastructure, government and power.",
"RXVT Technologies is no longer a subsidiary of the parent company."
]
all_sentences = relevant_sentences + irrelevant_sentences
query = "<query>: A company is a part of a larger company."
embeddings = encode_batch(sentence_encoder, tokenizer, all_sentences, "cpu").detach().cpu().numpy()
query_embedding = encode_batch(query_encoder, tokenizer, [query], "cpu").detach().cpu().numpy()
sims = cosine_similarity(query_embedding, embeddings)[0]
sentences_sims = list(zip(all_sentences, sims))
sentences_sims.sort(key=lambda x: x[1], reverse=True)
for s, sim in sentences_sims:
print(s, sim)
期待される出力
WHIRC – a subsidiary company of Wright-Hennepin 0.9396286
EM Microelectronic-Marin (subsidiary of The Swatch Group). 0.93929046
Fingersoft's parent company is the Finger Group. 0.936247
CK Life Sciences International (Holdings) Inc. (), or CK Life Sciences, is a subsidiary of CK Hutchison Holdings 0.9350312
The company is currently a division of the corporate group Jam Industries. 0.9273489
Volt Technical Resources is a business unit of Volt Workforce Solutions, a subsidiary of Volt Information Sciences (currently trading over-the-counter as VISI.). 0.9005086
The second company is deemed to be a subsidiary of the parent company. 0.6723645
It is a holding company that provides services through its subsidiaries in the following areas: oil and gas, industrial and infrastructure, government and power. 0.60081375
A parent company is a company that owns 51% or more voting stock in another firm (or subsidiary). 0.59490484
The company is owned by its employees. 0.55286574
RXVT Technologies is no longer a subsidiary of the parent company. 0.4321953
The company has gone through more than one incarnation. 0.38889483
Larger companies compete for market share by acquiring smaller companies that may own a particular market sector. 0.25472647
⚠️ 重要提示
このメソッドはデュアルエンコーダアーキテクチャを使用しています。これは文エンコーダであり、クエリエンコーダ と一緒に使用する必要があります。
📄 その他の情報
属性 |
详情 |
タグ |
特徴抽出、文の類似度 |
データセット |
biu-nlp/abstract-sim |
ウィジェット |
文の類似度、特徴抽出 |