{"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/neural-structural-correspondence-learning-for","title":"Neural Structural Correspondence Learning for Domain Adaptation","arxiv_id":"1610.01588","date":"2016-10-05","proceeding":"CONLL 2017 8","authors":["Yftah Ziser","Roi Reichart"],"abstract":"Domain adaptation, adapting models from domains rich in labeled training data\nto domains poor in such data, is a fundamental NLP challenge. We introduce a\nneural network model that marries together ideas from two prominent strands of\nresearch on domain adaptation through representation learning: structural\ncorrespondence learning (SCL, (Blitzer et al., 2006)) and autoencoder neural\nnetworks. Particularly, our model is a three-layer neural network that learns\nto encode the nonpivot features of an input example into a low-dimensional\nrepresentation, so that the existence of pivot features (features that are\nprominent in both domains and convey useful information for the NLP task) in\nthe example can be decoded from that representation. The low-dimensional\nrepresentation is then employed in a learning algorithm for the task. Moreover,\nwe show how to inject pre-trained word embeddings into our model in order to\nimprove generalization across examples with similar pivot features. On the task\nof cross-domain product sentiment classification (Blitzer et al., 2007),\nconsisting of 12 domain pairs, our model outperforms both the SCL and the\nmarginalized stacked denoising autoencoder (MSDA, (Chen et al., 2012)) methods\nby 3.77% and 2.17% respectively, on average across domain pairs.","url_abs":"http://arxiv.org/abs/1610.01588v3","url_pdf":"http://arxiv.org/pdf/1610.01588v3.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":"neural-structural-correspondence-learning-for","repo_url":"https://github.com/yftah89/Neural-SCLDomain-Adaptation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"neural-structural-correspondence-learning-for","repo_url":"https://github.com/yftah89/Neural-SCL-Domain-Adaptation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.01588","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}