Jan 30, 2023 · Artificial Intelligence

Domain Knowledge Enhanced Pretrained Language Model for Medicinal Product Vertical Search

This article presents a domain‑knowledge‑enhanced pretrained language model that combines ELECTRA‑based token‑level masking with a novel product‑attribute prediction (PAP) task to improve query understanding, intent classification, and relevance matching in vertical drug e‑commerce search, and validates its effectiveness through extensive experiments on public and proprietary datasets.

ELECTRAdomain knowledgemedical NLP

0 likes · 13 min read

Domain Knowledge Enhanced Pretrained Language Model for Medicinal Product Vertical Search

DataFunTalk

Nov 15, 2020 · Artificial Intelligence

Query Intent Recognition in Vertical Search: Challenges, Methods, and Case Studies

The article reviews the importance of query intent recognition in vertical search, outlines its definition, highlights practical challenges such as ambiguous input, multi‑intent queries, timeliness and cold‑start issues, and surveys common rule‑based, statistical, and machine‑learning solutions together with real‑world case studies.

NLUSearchcategory classification

0 likes · 17 min read