{"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/learning-to-rank-question-answer-pairs-using","title":"Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering","arxiv_id":"1710.03430","date":"2017-10-10","proceeding":"NAACL 2018 6","authors":["Seunghyun Yoon","Joongbo Shin","Kyomin Jung"],"abstract":"In this paper, we propose a novel end-to-end neural architecture for ranking\ncandidate answers, that adapts a hierarchical recurrent neural network and a\nlatent topic clustering module. With our proposed model, a text is encoded to a\nvector representation from an word-level to a chunk-level to effectively\ncapture the entire meaning. In particular, by adapting the hierarchical\nstructure, our model shows very small performance degradations in longer text\ncomprehension while other state-of-the-art recurrent neural network models\nsuffer from it. Additionally, the latent topic clustering module extracts\nsemantic information from target samples. This clustering module is useful for\nany text related tasks by allowing each data sample to find its nearest topic\ncluster, thus helping the neural network model analyze the entire data. We\nevaluate our models on the Ubuntu Dialogue Corpus and consumer electronic\ndomain question answering dataset, which is related to Samsung products. The\nproposed model shows state-of-the-art results for ranking question-answer\npairs.","url_abs":"http://arxiv.org/abs/1710.03430v3","url_pdf":"http://arxiv.org/pdf/1710.03430v3.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":"learning-to-rank-question-answer-pairs-using","repo_url":"https://github.com/david-yoon/QA_HRDE_LTC","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-rank-question-answer-pairs-using","repo_url":"https://github.com/aus10powell/Automated-Health-Responses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-rank-question-answer-pairs-using","repo_url":"https://github.com/younggns/comparative-abusive-lang","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/answer-selection-on-ubuntu-dialogue-v1","task":"Answer Selection","dataset":"Ubuntu Dialogue (v1, Ranking)","model":"HRDE-LTC","rank_in_archive_order":1,"of":1,"metrics":{"1 in 10 R@1":"0.684","1 in 10 R@2":"0.822","1 in 10 R@5":"0.960","1 in 2 R@1":"0.916"},"uses_additional_data":false},{"leaderboard":"/sota/answer-selection-on-ubuntu-dialogue-v2","task":"Answer Selection","dataset":"Ubuntu Dialogue (v2, Ranking)","model":"HRDE-LTC","rank_in_archive_order":2,"of":2,"metrics":{"1 in 10 R@1":"0.652","1 in 10 R@2":"0.815","1 in 10 R@5":"0.966","1 in 2 R@1":"0.915"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.03430","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}