document classification

58 Tech

Jun 18, 2021 · Artificial Intelligence

Bidding Document Classification and Entity Extraction Using BERT-based Models

This article describes how 58.com built an end‑to‑end bidding service that crawls tender documents, classifies them into multiple categories with BERT‑based models (including softmax, sigmoid and ensemble approaches) and extracts key entities using BERT‑CRF and reading‑comprehension techniques, achieving over 90% overall accuracy and dramatically improving recall and precision.