{"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/an-auto-encoder-matching-model-for-learning","title":"An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation","arxiv_id":"1808.08795","date":"2018-08-27","proceeding":"EMNLP 2018 10","authors":["Liangchen Luo","Jingjing Xu","Junyang Lin","Qi Zeng","Xu sun"],"abstract":"Generating semantically coherent responses is still a major challenge in\ndialogue generation. Different from conventional text generation tasks, the\nmapping between inputs and responses in conversations is more complicated,\nwhich highly demands the understanding of utterance-level semantic dependency,\na relation between the whole meanings of inputs and outputs. To address this\nproblem, we propose an Auto-Encoder Matching (AEM) model to learn such\ndependency. The model contains two auto-encoders and one mapping module. The\nauto-encoders learn the semantic representations of inputs and responses, and\nthe mapping module learns to connect the utterance-level representations.\nExperimental results from automatic and human evaluations demonstrate that our\nmodel is capable of generating responses of high coherence and fluency compared\nto baseline models. The code is available at https://github.com/lancopku/AMM","url_abs":"http://arxiv.org/abs/1808.08795v1","url_pdf":"http://arxiv.org/pdf/1808.08795v1.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":"an-auto-encoder-matching-model-for-learning","repo_url":"https://github.com/lancopku/AMM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-generation-on-dailydialog","task":"Text Generation","dataset":"DailyDialog","model":"AEM+Attention","rank_in_archive_order":1,"of":1,"metrics":{"BLEU-1":"14.17","BLEU-2":"5.69","BLEU-3":"3.78","BLEU-4":"2.84"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08795","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}