So sánh phương pháp

	Khử trùng văn bản	BERT Embeddings	TF-IDF
Lĩnh vực	Khai phá văn bản	Khai phá văn bản	Khai phá văn bản
Họ	Process / pipeline	Process / pipeline	Process / pipeline
Năm ra đời	1997	2019	1988
Người khởi xướng	Andrei Z. Broder (MinHash / Resemblance theory, 1997)	Devlin, Chang, Lee & Toutanova (Google AI)	Salton & Buckley
Loại	Text preprocessing / corpus quality pipeline	Contextual transformer text-representation method	Text vectorization / term-weighting scheme
Công trình gốc	Broder, A.Z. (1997). On the Resemblance and Containment of Documents. Compression and Complexity of SEQUENCES.	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Salton, G. & Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information Processing & Management, 24(5), 513-523.
Tên gọi khác	near-duplicate detection, document deduplication, corpus deduplication, Metin Tekilleştirme (Near-Duplicate Detection)	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	term weighting, tf-idf weighting, TF-IDF Vektörizasyonu
Liên quan	5	4	3
Tóm tắt	Text deduplication is a corpus-quality pipeline that identifies and removes exact and near-duplicate documents from large text collections. Grounded in Andrei Broder's 1997 resemblance theory, it is widely used to improve dataset quality for machine learning model training, search engine indexing, and any downstream NLP task that assumes a non-redundant corpus.	BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA.	TF-IDF, introduced by Salton and Buckley (1988), is a term-weighting scheme that scores each word in a document by how often it appears there and how rare it is across the whole collection. It turns raw text into weighted document vectors, giving high weight to terms that are frequent in one document but uncommon elsewhere.