{"url":"/method/skep","slug":"skep","name":"SKEP","full_name":"SKEP","full_name_withheld":false,"description_markdown":"**SKEP** is a self-supervised pre-training method for sentiment analysis. With the help of automatically-mined knowledge, SKEP conducts sentiment masking and constructs three sentiment knowledge prediction objectives, so as to embed sentiment information at the word, polarity and aspect level into pre-trained sentiment representation. In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair.\r\n\r\nSKEP contains two parts: (1) Sentiment masking recognizes the sentiment information of an input sequence based on automatically-mined sentiment knowledge, and produces a corrupted version by removing these informations. (2) Sentiment pre-training objectives require the transformer to recover the removed information from the corrupted version. The three prediction objectives on top are jointly optimized: Sentiment Word (SW) prediction (on $\\left.\\mathrm{x}\\_{9}\\right)$, Word Polarity (SP) prediction (on $\\mathrm{x}\\_{6}$ and $\\mathbf{x}\\_{9}$ ), Aspect-Sentiment pairs (AP) prediction (on $\\mathbf{x}\\_{1}$ ). Here, the smiley denotes positive polarity. Notably, on $\\mathrm{x}\\_{6}$, only SP is calculated without SW, as its original word has been predicted in the pair prediction on $\\mathbf{x}\\_{1}$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis","paper":"/paper/skep-sentiment-knowledge-enhanced-pre","first_author":"Hao Tian","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/skep-sentiment-knowledge-enhanced-pre"},"source":{"url":"https://arxiv.org/abs/2005.05635v2","title":"SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis","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":"Semi-Supervised Learning Methods","url":"/methods/category/semi-supervised-learning-methods","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/skep-sentiment-knowledge-enhanced-pre","title":"SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis","date":"2020-05-12","arxiv_id":"2005.05635","n_code_links":7,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/multi-label-classification-2","name":"MUlTI-LABEL-ClASSIFICATION","papers":1},{"task":"/task/multi-label-classification","name":"Multi-Label Classification","papers":1},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":1},{"task":"/task/stock-market-prediction","name":"Stock Market Prediction","papers":1}],"tasks_shown":4,"n_tasks":4,"usage_by_year":[{"year":"2020","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/skep"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}