{"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-context-sensitive-convolutional","title":"Learning Context-Sensitive Convolutional Filters for Text Processing","arxiv_id":"1709.08294","date":"2017-09-25","proceeding":"EMNLP 2018 10","authors":["Dinghan Shen","Martin Renqiang Min","Yitong Li","Lawrence Carin"],"abstract":"Convolutional neural networks (CNNs) have recently emerged as a popular\nbuilding block for natural language processing (NLP). Despite their success,\nmost existing CNN models employed in NLP share the same learned (and static)\nset of filters for all input sentences. In this paper, we consider an approach\nof using a small meta network to learn context-sensitive convolutional filters\nfor text processing. The role of meta network is to abstract the contextual\ninformation of a sentence or document into a set of input-aware filters. We\nfurther generalize this framework to model sentence pairs, where a\nbidirectional filter generation mechanism is introduced to encapsulate\nco-dependent sentence representations. In our benchmarks on four different\ntasks, including ontology classification, sentiment analysis, answer sentence\nselection, and paraphrase identification, our proposed model, a modified CNN\nwith context-sensitive filters, consistently outperforms the standard CNN and\nattention-based CNN baselines. By visualizing the learned context-sensitive\nfilters, we further validate and rationalize the effectiveness of proposed\nframework.","url_abs":"http://arxiv.org/abs/1709.08294v3","url_pdf":"http://arxiv.org/pdf/1709.08294v3.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":[],"tasks":[{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-yelp-binary","task":"Sentiment Analysis","dataset":"Yelp Binary classification","model":"M-ACNN","rank_in_archive_order":14,"of":20,"metrics":{"Error":"3.89"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-dbpedia","task":"Text Classification","dataset":"DBpedia","model":"M-ACNN","rank_in_archive_order":13,"of":21,"metrics":{"Error":"1.07"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}