How French Researchers Used Deep Learning to Predict 2.39 Million Anti‑Phage Proteins and Map Bacterial Immunity

A French team at the Pasteur Institute built three complementary deep‑learning models—ALBERT_DF, ESM_DF, and GeneCLR_DF—to predict anti‑phage proteins at genome scale, achieving 99% precision and 92% recall, and uncovered roughly 2.39 million candidate proteins and 23 000 novel operon families, dramatically expanding the known bacterial antiviral repertoire.

ALBERTDeep LearningESM

0 likes · 16 min read

How French Researchers Used Deep Learning to Predict 2.39 Million Anti‑Phage Proteins and Map Bacterial Immunity

HelloTech

Sep 13, 2023 · Artificial Intelligence

AI Platform‑Powered Automated Ticket Routing: Modeling Workflow, Feature Engineering, and Intent Recognition

The Haro AI platform automates customer‑service ticket routing by applying a four‑step pipeline—feature processing, model training, evaluation, and deployment—using BERT/ALBERT‑based intent recognition, configurable feature storage, AutoML or expert modes, and Faas‑style deployment, as demonstrated in the Universal Ticket System case study, dramatically improving accuracy and efficiency.

AI PlatformALBERTBERT

0 likes · 11 min read

AI Platform‑Powered Automated Ticket Routing: Modeling Workflow, Feature Engineering, and Intent Recognition

Tencent Cloud Developer

Mar 3, 2022 · Artificial Intelligence

Model Distillation for Query-Document Matching: Techniques and Optimizations

We applied knowledge distillation to a video query‑document BERT matcher, compressing the 12‑layer teacher into production‑ready 1‑layer ALBERT and tiny TextCNN students using combined soft, hard, and relevance losses plus AutoML‑tuned hyper‑parameters, achieving sub‑5 ms latency and up to 2.4% AUC improvement over the original model.

ALBERTAutoMLBERT

0 likes · 12 min read

Model Distillation for Query-Document Matching: Techniques and Optimizations

Xianyu Technology

Jan 19, 2021 · Artificial Intelligence

How Xianyu Extracts Second‑Hand Product Attributes with Albert‑Tiny and StructBert

This article analyzes Xianyu's second‑hand attribute extraction pipeline, detailing the challenges of sparse product data, the decomposition into NER and classification tasks, the use of Albert‑Tiny, StructBert and regex methods, deployment strategies, evaluation results, and future directions.

ALBERTInformation ExtractionNLP

0 likes · 11 min read

How Xianyu Extracts Second‑Hand Product Attributes with Albert‑Tiny and StructBert

How French Researchers Used Deep Learning to Predict 2.39 Million Anti‑Phage Proteins and Map Bacterial Immunity

AI Platform‑Powered Automated Ticket Routing: Modeling Workflow, Feature Engineering, and Intent Recognition

Model Distillation for Query-Document Matching: Techniques and Optimizations

How Xianyu Extracts Second‑Hand Product Attributes with Albert‑Tiny and StructBert

How French Researchers Used Deep Learning to Predict 2.39 Million Anti‑Phage Proteins and Map Bacterial Immunity