{"url":"/method/knowprompt","slug":"knowprompt","name":"KnowPrompt","full_name":"KnowPrompt","full_name_withheld":false,"description_markdown":"**KnowPrompt** is a prompt-tuning approach for relational understanding. It injects entity and relation knowledge into prompt construction with learnable virtual template words as well as answer words and synergistically optimize their representation with knowledge constraints. To be specific, TYPED MARKER is utilized around entities initialized with aggregated entity-type embeddings as learnable virtual template words to inject entity type knowledge. The average embeddings of each token are leveraged in relation labels as virtual answer words to inject relation knowledge. Since there exist implicit structural constraints among entities and relations, and virtual words should be consistent with the surrounding contexts, synergistic optimization is introduced to obtain optimized virtual templates and answer words. Concretely, a context-aware prompt calibration method is used with implicit structural constraints to inject structural knowledge implications among relational triples and associate prompt embeddings with each other.","description_state":"present","introduced_year":null,"introduced_by":{"title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","paper":"/paper/adaprompt-adaptive-prompt-based-finetuning","first_author":"Xiang Chen","n_authors":9,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/adaprompt-adaptive-prompt-based-finetuning"},"source":{"url":"https://arxiv.org/abs/2104.07650v7","title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Prompt Engineering","url":"/methods/category/prompt-engineering","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":"/paper/exploring-prompting-large-language-models-as","title":"Exploring Prompting Large Language Models as Explainable Metrics","date":"2023-11-20","arxiv_id":"2311.11552","n_code_links":1,"syntology":null},{"paper":"/paper/decoupling-knowledge-from-memorization","title":"Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning","date":"2022-05-29","arxiv_id":"2205.14704","n_code_links":2,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":"/paper/relation-extraction-as-open-book-examination","title":"Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning","date":"2022-05-04","arxiv_id":"2205.02355","n_code_links":1,"syntology":null},{"paper":"/paper/easynlp-a-comprehensive-and-easy-to-use","title":"EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing","date":"2022-04-30","arxiv_id":"2205.00258","n_code_links":1,"syntology":null},{"paper":"/paper/deepke-a-deep-learning-based-knowledge","title":"DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population","date":"2022-01-10","arxiv_id":"2201.03335","n_code_links":1,"syntology":null},{"paper":"/paper/adaprompt-adaptive-prompt-based-finetuning","title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","date":"2021-04-15","arxiv_id":"2104.07650","n_code_links":1,"syntology":null}],"papers_shown":6,"tasks":[{"task":"/task/relation-extraction","name":"Relation Extraction","papers":4},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":2},{"task":"/task/memorization","name":"Memorization","papers":2},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":2},{"task":"/task/prompt-engineering","name":"Prompt Engineering","papers":2},{"task":null,"name":"Relation","papers":2},{"task":"/task/retrieval","name":"Retrieval","papers":2},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/attribute-extraction","name":"Attribute Extraction","papers":1},{"task":"/task/cross-domain-named-entity-recognition","name":"Cross-Domain Named Entity Recognition","papers":1},{"task":"/task/dialog-relation-extraction","name":"Dialog Relation Extraction","papers":1},{"task":"/task/few-shot-text-classification","name":"Few-Shot Text Classification","papers":1},{"task":"/task/knowledge-base-population","name":"Knowledge Base Population","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":1},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":1},{"task":"/task/prompt-learning","name":"Prompt Learning","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1}],"tasks_shown":20,"n_tasks":23,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":4},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/knowprompt"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}