{"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/multiresolution-recurrent-neural-networks-an","title":"Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation","arxiv_id":"1606.00776","date":"2016-06-02","proceeding":null,"authors":["Iulian Vlad Serban","Tim Klinger","Gerald Tesauro","Kartik Talamadupula","Bo-Wen Zhou","Yoshua Bengio","Aaron Courville"],"abstract":"We introduce the multiresolution recurrent neural network, which extends the\nsequence-to-sequence framework to model natural language generation as two\nparallel discrete stochastic processes: a sequence of high-level coarse tokens,\nand a sequence of natural language tokens. There are many ways to estimate or\nlearn the high-level coarse tokens, but we argue that a simple extraction\nprocedure is sufficient to capture a wealth of high-level discourse semantics.\nSuch procedure allows training the multiresolution recurrent neural network by\nmaximizing the exact joint log-likelihood over both sequences. In contrast to\nthe standard log- likelihood objective w.r.t. natural language tokens (word\nperplexity), optimizing the joint log-likelihood biases the model towards\nmodeling high-level abstractions. We apply the proposed model to the task of\ndialogue response generation in two challenging domains: the Ubuntu technical\nsupport domain, and Twitter conversations. On Ubuntu, the model outperforms\ncompeting approaches by a substantial margin, achieving state-of-the-art\nresults according to both automatic evaluation metrics and a human evaluation\nstudy. On Twitter, the model appears to generate more relevant and on-topic\nresponses according to automatic evaluation metrics. Finally, our experiments\ndemonstrate that the proposed model is more adept at overcoming the sparsity of\nnatural language and is better able to capture long-term structure.","url_abs":"http://arxiv.org/abs/1606.00776v2","url_pdf":"http://arxiv.org/pdf/1606.00776v2.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":"multiresolution-recurrent-neural-networks-an","repo_url":"https://github.com/julianser/Ubuntu-Multiresolution-Tools","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"multiresolution-recurrent-neural-networks-an","repo_url":"https://github.com/WolfNiu/AdversarialDialogue","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multiresolution-recurrent-neural-networks-an","repo_url":"https://github.com/julianser/hed-dlg-truncated","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"multiresolution-recurrent-neural-networks-an","repo_url":"https://github.com/wayalhruhi/julianser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-generation-on-twitter-dialogue-noun","task":"Dialogue Generation","dataset":"Twitter Dialogue (Noun)","model":"MrRNN Act.-Ent.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"4.63","Precision":"4.82","Recall":"5.22"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-generation-on-twitter-dialogue-tense","task":"Dialogue Generation","dataset":"Twitter Dialogue (Tense)","model":"MrRNN Act.-Ent.","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"34.48%"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-generation-on-ubuntu-dialogue","task":"Dialogue Generation","dataset":"Ubuntu Dialogue (Activity)","model":"MrRNN Act.-Ent.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"11.43","Precision":"16.84","Recall":"9.72"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-generation-on-ubuntu-dialogue-cmd","task":"Dialogue Generation","dataset":"Ubuntu Dialogue (Cmd)","model":"MrRNN Act.-Ent.","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"95.04%"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-generation-on-ubuntu-dialogue-entity","task":"Dialogue Generation","dataset":"Ubuntu Dialogue (Entity)","model":"MrRNN Act.-Ent.","rank_in_archive_order":1,"of":1,"metrics":{"F1":"3.72","Precision":"4.91","Recall":"3.36"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-generation-on-ubuntu-dialogue-tense","task":"Dialogue Generation","dataset":"Ubuntu Dialogue (Tense)","model":"MrRNN Act.-Ent.","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"29.01%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.00776","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}