{"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-compare-aggregate-model-for-matching-text","title":"A Compare-Aggregate Model for Matching Text Sequences","arxiv_id":"1611.01747","date":"2016-11-06","proceeding":null,"authors":["Shuohang Wang","Jing Jiang"],"abstract":"Many NLP tasks including machine comprehension, answer selection and text\nentailment require the comparison between sequences. Matching the important\nunits between sequences is a key to solve these problems. In this paper, we\npresent a general \"compare-aggregate\" framework that performs word-level\nmatching followed by aggregation using Convolutional Neural Networks. We\nparticularly focus on the different comparison functions we can use to match\ntwo vectors. We use four different datasets to evaluate the model. We find that\nsome simple comparison functions based on element-wise operations can work\nbetter than standard neural network and neural tensor network.","url_abs":"http://arxiv.org/abs/1611.01747v1","url_pdf":"http://arxiv.org/pdf/1611.01747v1.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-compare-aggregate-model-for-matching-text","repo_url":"https://github.com/shuohangwang/SeqMatchSeq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"a-compare-aggregate-model-for-matching-text","repo_url":"https://github.com/DigitalPhonetics/reading-comprehension","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01747","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}