{"url":"/method/ernie","slug":"ernie","name":"ERNIE","full_name":"ERNIE","full_name_withheld":false,"description_markdown":"ERNIE is a transformer-based model consisting of two stacked modules: 1) textual encoder and 2) knowledgeable encoder, which is responsible to integrate extra token-oriented knowledge information into textual information. This layer consists of stacked aggregators, designed for encoding both tokens and entities as well as fusing their heterogeneous features. To integrate this layer of enhancing representations via knowledge, a special pre-training task is adopted for ERNIE - it involves randomly masking token-entity alignments and training the model to predict all corresponding entities based on aligned tokens (aka denoising entity auto-encoder).","description_state":"present","introduced_year":null,"introduced_by":{"title":"ERNIE: Enhanced Representation through Knowledge Integration","paper":"/paper/ernie-enhanced-representation-through","first_author":"Yu Sun","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/ernie-enhanced-representation-through"},"source":{"url":"http://arxiv.org/abs/1904.09223v1","title":"ERNIE: Enhanced Representation through Knowledge Integration","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":54,"archive_num_papers":54,"papers_newest_first":[{"paper":"/paper/evaluating-moral-beliefs-across-llms-through","title":"Evaluating Moral Beliefs across LLMs through a Pluralistic Framework","date":"2024-11-06","arxiv_id":"2411.03665","n_code_links":1,"syntology":null},{"paper":null,"title":"The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams","date":"2024-10-31","arxiv_id":"2410.23769","n_code_links":0,"syntology":null},{"paper":null,"title":"Testing Large Language Models on Driving Theory Knowledge and Skills for Connected Autonomous Vehicles","date":"2024-07-24","arxiv_id":"2407.17211","n_code_links":0,"syntology":null},{"paper":null,"title":"Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research","date":"2024-07-22","arxiv_id":"2407.21045","n_code_links":0,"syntology":null},{"paper":null,"title":"The Solution for the AIGC Inference Performance Optimization Competition","date":"2024-07-06","arxiv_id":"2407.04991","n_code_links":0,"syntology":null},{"paper":null,"title":"Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba","date":"2024-06-18","arxiv_id":"2406.12754","n_code_links":0,"syntology":null},{"paper":"/paper/newsbench-systematic-evaluation-of-llms-for","title":"NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism","date":"2024-02-29","arxiv_id":"2403.00862","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":0}},{"paper":null,"title":"Research about the Ability of LLM in the Tamper-Detection Area","date":"2024-01-24","arxiv_id":"2401.13504","n_code_links":0,"syntology":null},{"paper":"/paper/how-robust-is-google-s-bard-to-adversarial","title":"How Robust is Google's Bard to Adversarial Image Attacks?","date":"2023-09-21","arxiv_id":"2309.11751","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}},{"paper":"/paper/robust-multi-agent-reinforcement-learning-via","title":"Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"The Impact of Artificial Intelligence on the Evolution of Digital Education: A Comparative Study of OpenAI Text Generation Tools including ChatGPT, Bing Chat, Bard, and Ernie","date":"2023-09-05","arxiv_id":"2309.02029","n_code_links":0,"syntology":null},{"paper":null,"title":"An APT Event Extraction Method Based on BERT-BiGRU-CRF for APT Attack Detection","date":"2023-08-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/towards-effective-ancient-chinese-translation","title":"Towards Effective Ancient Chinese Translation: Dataset, Model, and Evaluation","date":"2023-08-01","arxiv_id":"2308.00240","n_code_links":1,"syntology":null},{"paper":null,"title":"HouYi: An open-source large language model specially designed for renewable energy and carbon neutrality field","date":"2023-07-31","arxiv_id":"2308.01414","n_code_links":0,"syntology":null},{"paper":null,"title":"MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine","date":"2023-05-12","arxiv_id":"2305.07340","n_code_links":0,"syntology":null},{"paper":"/paper/impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","n_code_links":2,"syntology":null},{"paper":"/paper/co-driven-recognition-of-semantic-consistency","title":"Co-Driven Recognition of Semantic Consistency via the Fusion of Transformer and HowNet Sememes Knowledge","date":"2023-02-21","arxiv_id":"2302.10570","n_code_links":1,"syntology":null},{"paper":"/paper/ernie-3-0-tiny-frustratingly-simple-method-to","title":"ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization","date":"2023-01-09","arxiv_id":"2301.03416","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":0}},{"paper":"/paper/vote-n-rank-revision-of-benchmarking-with","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","date":"2022-10-11","arxiv_id":"2210.05769","n_code_links":1,"syntology":{"ran":0,"of":17,"unverified":17,"pointer_only":0}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","n_code_links":9,"syntology":{"ran":5,"of":21,"unverified":16,"pointer_only":0}},{"paper":null,"title":"ARGUABLY@SMM4H’22: Classification of Health Related Tweets using Ensemble, Zero-Shot and Fine-Tuned Language Model","date":"2022-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-word-semantics-to-enrich-character","title":"Exploiting Word Semantics to Enrich Character Representations of Chinese Pre-trained Models","date":"2022-07-13","arxiv_id":"2207.05928","n_code_links":1,"syntology":null},{"paper":"/paper/argumentative-text-generation-in-economic","title":"Argumentative Text Generation in Economic Domain","date":"2022-06-18","arxiv_id":"2206.09251","n_code_links":1,"syntology":null},{"paper":null,"title":"Automatic Summarization of Russian Texts: Comparison of Extractive and Abstractive Methods","date":"2022-06-18","arxiv_id":"2206.09253","n_code_links":0,"syntology":null},{"paper":"/paper/training-on-lexical-resources","title":"Training on Lexical Resources","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-chinese-pre-trained-language-model","title":"Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph","date":"2022-05-01","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":"/paper/idiap-submission-lt-edi-acl2022-hope-speech","title":"IDIAP Submission@LT-EDI-ACL2022 : Hope Speech Detection for Equality, Diversity and Inclusion","date":"2022-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Research on Dual Channel News Headline Classification Based on ERNIE Pre-training Model","date":"2022-02-14","arxiv_id":"2202.06600","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-knowledge-integration-in-1","title":"What Has Been Enhanced in my Knowledge-Enhanced Language Model?","date":"2022-02-02","arxiv_id":"2202.00964","n_code_links":1,"syntology":null},{"paper":"/paper/ernie-3-0-titan-exploring-larger-scale","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-12-23","arxiv_id":"2112.12731","n_code_links":3,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":16},{"task":"/task/language-modeling","name":"Language Modeling","papers":12},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":5},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":5},{"task":"/task/sentence","name":"Sentence","papers":5},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":5},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":4},{"task":"/task/question-answering","name":"Question Answering","papers":4},{"task":"/task/benchmarking","name":"Benchmarking","papers":3},{"task":"/task/classification-1","name":"Classification","papers":3},{"task":null,"name":"GPU","papers":3},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":3},{"task":"/task/knowledge-graphs","name":"Knowledge Graphs","papers":3},{"task":"/task/cg","name":"NER","papers":3},{"task":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity","papers":3},{"task":"/task/text-generation","name":"Text Generation","papers":3},{"task":"/task/named-entity-recognition","name":"named-entity-recognition","papers":3},{"task":null,"name":"CPU","papers":2},{"task":"/task/chinese-named-entity-recognition","name":"Chinese Named Entity Recognition","papers":2},{"task":"/task/chinese-sentence-pair-classification","name":"Chinese Sentence Pair Classification","papers":2}],"tasks_shown":20,"n_tasks":94,"usage_by_year":[{"year":"2019","papers":4},{"year":"2020","papers":8},{"year":"2021","papers":13},{"year":"2022","papers":11},{"year":"2023","papers":10},{"year":"2024","papers":8}],"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/ernie"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}