{"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-fully-attention-based-information-retriever","title":"A Fully Attention-Based Information Retriever","arxiv_id":"1810.09580","date":"2018-10-22","proceeding":null,"authors":["Alvaro Henrique Chaim Correia","Jorge Luiz Moreira Silva","Thiago de Castro Martins","Fabio Gagliardi Cozman"],"abstract":"Recurrent neural networks are now the state-of-the-art in natural language\nprocessing because they can build rich contextual representations and process\ntexts of arbitrary length. However, recent developments on attention mechanisms\nhave equipped feedforward networks with similar capabilities, hence enabling\nfaster computations due to the increase in the number of operations that can be\nparallelized. We explore this new type of architecture in the domain of\nquestion-answering and propose a novel approach that we call Fully Attention\nBased Information Retriever (FABIR). We show that FABIR achieves competitive\nresults in the Stanford Question Answering Dataset (SQuAD) while having fewer\nparameters and being faster at both learning and inference than rival methods.","url_abs":"http://arxiv.org/abs/1810.09580v1","url_pdf":"http://arxiv.org/pdf/1810.09580v1.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-fully-attention-based-information-retriever","repo_url":"https://github.com/AlCorreia/FABIR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"FABIR","rank_in_archive_order":172,"of":213,"metrics":{"EM":"67.744","F1":"77.605"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"FABIR","rank_in_archive_order":46,"of":55,"metrics":{"EM":"65.1","F1":"75.6"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}