{"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/harnessing-deep-neural-networks-with-logic","title":"Harnessing Deep Neural Networks with Logic Rules","arxiv_id":"1603.06318","date":"2016-03-21","proceeding":"ACL 2016 8","authors":["Zhiting Hu","Xuezhe Ma","Zhengzhong Liu","Eduard Hovy","Eric Xing"],"abstract":"Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop an iterative distillation method that transfers the structured information of logic rules into the weights of neural networks. We deploy the framework on a CNN for sentiment analysis, and an RNN for named entity recognition. With a few highly intuitive rules, we obtain substantial improvements and achieve state-of-the-art or comparable results to previous best-performing systems.","url_abs":"https://arxiv.org/abs/1603.06318v6","url_pdf":"https://arxiv.org/pdf/1603.06318v6.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":"harnessing-deep-neural-networks-with-logic","repo_url":"https://github.com/ZhitingHu/logicnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"harnessing-deep-neural-networks-with-logic","repo_url":"https://github.com/martiansideofthemoon/logic-rules-sentiment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"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":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"Bi-LSTM + Logic rules","rank_in_archive_order":69,"of":73,"metrics":{"F1":"91.18"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"CNN + Logic rules","rank_in_archive_order":65,"of":87,"metrics":{"Accuracy":"89.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.06318","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}