{"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-paraphrase-generation-with-stacked","title":"Neural Paraphrase Generation with Stacked Residual LSTM Networks","arxiv_id":"1610.03098","date":"2016-10-10","proceeding":"COLING 2016 12","authors":["Aaditya Prakash","Sadid A. Hasan","Kathy Lee","Vivek Datla","Ashequl Qadir","Joey Liu","Oladimeji Farri"],"abstract":"In this paper, we propose a novel neural approach for paraphrase generation.\nConventional para- phrase generation methods either leverage hand-written rules\nand thesauri-based alignments, or use statistical machine learning principles.\nTo the best of our knowledge, this work is the first to explore deep learning\nmodels for paraphrase generation. Our primary contribution is a stacked\nresidual LSTM network, where we add residual connections between LSTM layers.\nThis allows for efficient training of deep LSTMs. We evaluate our model and\nother state-of-the-art deep learning models on three different datasets: PPDB,\nWikiAnswers and MSCOCO. Evaluation results demonstrate that our model\noutperforms sequence to sequence, attention-based and bi- directional LSTM\nmodels on BLEU, METEOR, TER and an embedding-based sentence similarity metric.","url_abs":"http://arxiv.org/abs/1610.03098v3","url_pdf":"http://arxiv.org/pdf/1610.03098v3.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-paraphrase-generation-with-stacked","repo_url":"https://github.com/pushpendughosh/Stock-market-forecasting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"paraphrase-generation","task_name":"Paraphrase Generation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-similarity","task_name":"Sentence Similarity"}],"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":{"syntology_url":"https://syntology.ai/paper/1610.03098","atlas_url":"https://app.syntology.ai/?focus=1610.03098","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}