{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-domain-knowledge-enhanced-pre-trained","title":"A Domain Knowledge Enhanced Pre-Trained Language Model for Vertical Search: Case Study on Medicinal Products","arxiv_id":null,"date":"2022-10-01","proceeding":"COLING 2022 10","authors":["Kesong Liu","Jianhui Jiang","Feifei Lyu"],"abstract":"We present a biomedical knowledge enhanced pre-trained language model for medicinal product vertical search. Following ELECTRA’s replaced token detection (RTD) pre-training, we leverage biomedical entity masking (EM) strategy to learn better contextual word representations. Furthermore, we propose a novel pre-training task, product attribute prediction (PAP), to inject product knowledge into the pre-trained language model efficiently by leveraging medicinal product databases directly. By sharing the parameters of PAP’s transformer encoder with that of RTD’s main transformer, these two pre-training tasks are jointly learned. Experiments demonstrate the effectiveness of PAP task for pre-trained language model on medicinal product vertical search scenario, which includes query-title relevance, query intent classification, and named entity recognition in query.","url_abs":"https://aclanthology.org/2022.coling-1.85","url_pdf":"https://aclanthology.org/2022.coling-1.85.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-domain-knowledge-enhanced-pre-trained","repo_url":"https://github.com/liuks/ep_plm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"intent-classification-1","task_name":"intent-classification"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}