Tagged articles
semantic similarity
11 articles · Page 1 of 1
The paper presents a systematic testing framework for large‑model interaction capabilities, identifies five unique testing challenges, defines four core abilities (basic dialogue, information extraction, intent recognition, process decision), proposes a semantic‑vector automated verification method, and reports pilot results showing significant efficiency gains and defect detection improvements in a banking context.
Testing Frameworkautomated testingbanking AI
0 likes · 14 min read


Qborfy AIAug 25, 2025 · Artificial Intelligence
This article explains how embeddings transform discrete items such as text, images, or user actions into continuous vectors, walks through the step‑by‑step workflow—from tokenization to normalization—highlights core properties, compares popular models, and showcases practical use cases in e‑commerce intent filtering and medical image retrieval, all backed by concrete examples and code.
AI Fundamentalsembeddingsmodel comparison
0 likes · 7 min read

This article explains the fundamentals of word vectors in NLP, walks through constructing them via co‑occurrence matrices and dimensionality reduction, demonstrates the process with a concrete example and Python code, and evaluates the resulting embeddings using cosine similarity.
NLPPythonSVD
0 likes · 7 min read

This article walks through a Python solution for semantic similarity using Word2Vec, showing the problem context, required data preprocessing, the exact code implementation, and the resulting output, while also offering practical tips for asking technical questions in community groups.
GensimNLPWord2Vec
0 likes · 4 min read

This article proposes a dual‑mode detection solution for call‑recording quality inspection that combines rule‑based semantic similarity matching with BERT‑based sentence segmentation and RoBERTa multi‑label classification to achieve high accuracy, fast task adaptation, and strong generalization for customer‑service scenarios.
BERTNLPRoBERTa
0 likes · 7 min read

This article describes how Haodf Online improved its medical question‑answer search by analyzing search challenges, adopting semantic similarity models based on pre‑trained language embeddings, designing contrastive training tasks, and evaluating the resulting increase in click‑through rate and user engagement.
medical AImodel optimizationnatural language processing
0 likes · 12 min read

ConSERT introduces a contrastive self‑supervised framework that enhances BERT‑derived sentence embeddings by applying efficient embedding‑level data augmentations, achieving significant improvements on semantic textual similarity tasks, especially in low‑resource settings, and outperforming previous state‑of‑the‑art methods.
BERTContrastive Learningself-supervised
0 likes · 20 min read

ConSERT is a contrastive self‑supervised framework that fine‑tunes BERT with augmented sentence views and NT‑Xent loss to overcome embedding collapse, delivering roughly 8% higher STS performance than prior methods, remaining robust in few‑shot and supervised scenarios, and now deployed in Meituan’s NLP pipelines.
BERTContrastive LearningNLP
0 likes · 20 min read

At Baidu Search, a large‑scale short‑text clustering system was built using multi‑level semantic splitting, fine‑grained aggregation and error‑correction, evolving from v1.0 to v2.0, and now clusters 100 million queries with 95 % accuracy and 80 % recall within three days.
Unsupervised Learningmulti-level splittingsearch query processing
0 likes · 19 min read

AlphaEmbedding builds a weighted graph linking Chinese words, sub‑words, characters and pinyin, then uses random‑walk‑based node2vec training to produce embeddings that capture orthographic and phonetic similarity, markedly improving recall and ranking for homophones, typos and OOV terms in enterprise search.
Chinese NLPgraph computingsemantic similarity
0 likes · 17 min read


58 TechOct 16, 2019 · Artificial Intelligence
This article details the architecture and algorithms behind a voice robot's natural language understanding module, covering single‑sentence intent classification with TextCNN, acoustic quality detection using VGGish‑BiLSTM, semantic similarity matching via DSSM and TextCNN‑Transformer, and slot‑filling with IDCNN‑CRF, along with performance results and future directions.
AINLUTextCNN
0 likes · 11 min read
