Tagged articles
text representation
10 articles · Page 1 of 1
This survey reviews the evolution of semantic embedding—from Word2vec and GloVe to BERT, Sentence‑BERT, and recent contrastive methods—then examines how large language models improve embeddings via synthetic data generation and backbone architectures, detailing techniques such as contrastive prompting, in‑context learning, knowledge distillation, and discussing resource, privacy, and interpretability challenges.
Contrastive LearningNLPin-context learning
0 likes · 27 min read

This article reviews how large language models (LLMs) enhance semantic text embeddings by comparing traditional methods with LLM‑based approaches, detailing synthetic data generation, backbone model designs, key model families, experimental results on the MTEB benchmark, and future research challenges.
Contrastive LearningLLMmodel comparison
0 likes · 30 min read


JavaEdgeMar 11, 2025 · Artificial Intelligence
This tutorial explains how to transform raw text into tensor representations using one‑hot encoding, Word2Vec, and FastText, provides step‑by‑step code examples, discusses their advantages and drawbacks, and shows how to visualize embeddings with TensorBoard.
TensorWord2VecfastText
0 likes · 8 min read

This article introduces the ModelScope community's suite of foundational NLP models—including tokenization, POS tagging, NER, and text representation—detailing their architectures, performance, application scenarios, while also highlighting research contributions such as the ACE framework and retrieval‑enhanced techniques.
ModelScopeNLPartificial intelligence
0 likes · 21 min read

ArcCSE introduces an angular‑margin contrastive loss and both pairwise (dropout‑augmented) and triple‑wise (span‑masked) relationship modeling to self‑supervise text embeddings, yielding tighter decision boundaries, higher alignment and uniformity, and superior performance on unsupervised STS, SentEval, and Alibaba’s retrieval and recommendation systems.
Contrastive LearningNLPSelf-Supervised Learning
0 likes · 8 min read

This article explores how AI techniques such as deep semantic matching, attention mechanisms, variational autoencoders, and neural topic models can transform traditional recruitment by improving person‑job matching, interview assistance, and text representation, supported by experiments on real‑world hiring data.
AI recruitmentVAEinterview assistance
0 likes · 18 min read

This article presents a comprehensive overview of applying AI techniques—semantic matching models, attention mechanisms, VAE‑based text representation, and neural topic models—to improve talent acquisition, candidate‑job matching, interview assistance, and recruitment text analysis, supported by experiments on real‑world hiring data.
AI in HRIntelligent RecruitmentNeural Topic Model
0 likes · 19 min read


58 TechAug 5, 2021 · Artificial Intelligence
This article presents a comprehensive study of text representation techniques—from weighted word‑vector methods to supervised SimBert and unsupervised contrastive learning models—applied to large‑scale unstructured data in 58's information‑security workflows, evaluating their effectiveness for classification and content‑recall tasks.
BERTContrastive LearningPretrained Models
0 likes · 11 min read

This article presents a study on enhancing text representation and clustering in a small‑sample setting for 58's second‑hand car intelligent customer service by introducing a Bi‑LSTM based pre‑training language model and an improved Deep Embedded Clustering (DEC) algorithm, demonstrating significant gains in accuracy, silhouette score, and answer‑rate through extensive experiments.
AIBi-LSTMDEC
0 likes · 16 min read


58 TechMay 15, 2020 · Artificial Intelligence
This article presents a study on enhancing text representation and clustering purity in the small‑sample 58.com used‑car customer‑service scenario by introducing a Bi‑LSTM based pre‑trained language model and an improved Deep Embedded Clustering (DEC) algorithm, demonstrating significant gains in accuracy, silhouette score, and answer‑rate.
Bi-LSTMCustomer ServiceDEC
0 likes · 16 min read
