{"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/a-hierarchical-neural-autoencoder-for","title":"A Hierarchical Neural Autoencoder for Paragraphs and Documents","arxiv_id":"1506.01057","date":"2015-06-02","proceeding":"IJCNLP 2015 7","authors":["Jiwei Li","Minh-Thang Luong","Dan Jurafsky"],"abstract":"Natural language generation of coherent long texts like paragraphs or longer\ndocuments is a challenging problem for recurrent networks models. In this\npaper, we explore an important step toward this generation task: training an\nLSTM (Long-short term memory) auto-encoder to preserve and reconstruct\nmulti-sentence paragraphs. We introduce an LSTM model that hierarchically\nbuilds an embedding for a paragraph from embeddings for sentences and words,\nthen decodes this embedding to reconstruct the original paragraph. We evaluate\nthe reconstructed paragraph using standard metrics like ROUGE and Entity Grid,\nshowing that neural models are able to encode texts in a way that preserve\nsyntactic, semantic, and discourse coherence. While only a first step toward\ngenerating coherent text units from neural models, our work has the potential\nto significantly impact natural language generation and\nsummarization\\footnote{Code for the three models described in this paper can be\nfound at www.stanford.edu/~jiweil/ .","url_abs":"http://arxiv.org/abs/1506.01057v2","url_pdf":"http://arxiv.org/pdf/1506.01057v2.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":"a-hierarchical-neural-autoencoder-for","repo_url":"https://github.com/guanliu321/CNN-RNN-HAN-for-Text-Classification-Using-NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-hierarchical-neural-autoencoder-for","repo_url":"https://github.com/rachit-shah/News-Classfication-using-DNN-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-hierarchical-neural-autoencoder-for","repo_url":"https://github.com/tuvuumass/SCoPE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-hierarchical-neural-autoencoder-for","repo_url":"https://github.com/jiweil/Hierarchical-Neural-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-hierarchical-neural-autoencoder-for","repo_url":"https://github.com/lipiji/hierarchical-encoder-decoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.01057","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}