{"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/glomo-unsupervisedly-learned-relational","title":"GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations","arxiv_id":"1806.05662","date":"2018-06-14","proceeding":null,"authors":["Zhilin Yang","Jake Zhao","Bhuwan Dhingra","Kaiming He","William W. Cohen","Ruslan Salakhutdinov","Yann Lecun"],"abstract":"Modern deep transfer learning approaches have mainly focused on learning\ngeneric feature vectors from one task that are transferable to other tasks,\nsuch as word embeddings in language and pretrained convolutional features in\nvision. However, these approaches usually transfer unary features and largely\nignore more structured graphical representations. This work explores the\npossibility of learning generic latent relational graphs that capture\ndependencies between pairs of data units (e.g., words or pixels) from\nlarge-scale unlabeled data and transferring the graphs to downstream tasks. Our\nproposed transfer learning framework improves performance on various tasks\nincluding question answering, natural language inference, sentiment analysis,\nand image classification. We also show that the learned graphs are generic\nenough to be transferred to different embeddings on which the graphs have not\nbeen trained (including GloVe embeddings, ELMo embeddings, and task-specific\nRNN hidden unit), or embedding-free units such as image pixels.","url_abs":"http://arxiv.org/abs/1806.05662v3","url_pdf":"http://arxiv.org/pdf/1806.05662v3.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":"glomo-unsupervisedly-learned-relational","repo_url":"https://github.com/YJHMITWEB/GLoMo-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"elmo","method_name":"ELMo"},{"method_slug":"glove","method_name":"GloVe"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.05662","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}