{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/densely-connected-attention-propagation-for","title":"Densely Connected Attention Propagation for Reading Comprehension","arxiv_id":"1811.04210","date":"2018-11-10","proceeding":"NeurIPS 2018 12","authors":["Yi Tay","Luu Anh Tuan","Siu Cheung Hui","Jian Su"],"abstract":"We propose DecaProp (Densely Connected Attention Propagation), a new densely\nconnected neural architecture for reading comprehension (RC). There are two\ndistinct characteristics of our model. Firstly, our model densely connects all\npairwise layers of the network, modeling relationships between passage and\nquery across all hierarchical levels. Secondly, the dense connectors in our\nnetwork are learned via attention instead of standard residual skip-connectors.\nTo this end, we propose novel Bidirectional Attention Connectors (BAC) for\nefficiently forging connections throughout the network. We conduct extensive\nexperiments on four challenging RC benchmarks. Our proposed approach achieves\nstate-of-the-art results on all four, outperforming existing baselines by up to\n$2.6\\%-14.2\\%$ in absolute F1 score.","url_abs":"http://arxiv.org/abs/1811.04210v2","url_pdf":"http://arxiv.org/pdf/1811.04210v2.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":"densely-connected-attention-propagation-for","repo_url":"https://github.com/ajenningsfrankston/NIPS2018_DECAPROP-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"densely-connected-attention-propagation-for","repo_url":"https://github.com/vanzytay/NIPS2018_DECAPROP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-quasar","task":"Open-Domain Question Answering","dataset":"Quasar","model":"DecaProp","rank_in_archive_order":3,"of":6,"metrics":{"EM (Quasar-T)":"38.6","F1 (Quasar-T)":"46.9"},"uses_additional_data":false},{"leaderboard":"/sota/open-domain-question-answering-on-searchqa","task":"Open-Domain Question Answering","dataset":"SearchQA","model":"DECAPROP","rank_in_archive_order":5,"of":14,"metrics":{"EM":"62.2"},"uses_additional_data":false},{"leaderboard":"/sota/open-domain-question-answering-on-searchqa","task":"Open-Domain Question Answering","dataset":"SearchQA","model":"DecaProp","rank_in_archive_order":7,"of":14,"metrics":{"EM":"56.8","F1":"63.6","N-gram F1":"70.8","Unigram Acc":"62.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-narrativeqa","task":"Question Answering","dataset":"NarrativeQA","model":"DecaProp","rank_in_archive_order":5,"of":10,"metrics":{"BLEU-1":"44.35","BLEU-4":"27.61","METEOR":"21.80","Rouge-L":"44.69"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-newsqa","task":"Question Answering","dataset":"NewsQA","model":"DecaProp","rank_in_archive_order":12,"of":18,"metrics":{"EM":"53.1","F1":"66.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-quasart-t","task":"Question Answering","dataset":"Quasart-T","model":"DECAPROP","rank_in_archive_order":6,"of":7,"metrics":{"EM":"38.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.04210","atlas_url":"https://app.syntology.ai/?focus=1811.04210","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1811.04210"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.04210\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.04210"},"call":"get_concepts_for_paper(arxiv_id=\"1811.04210\")"}],"by_repo":[{"repo":"ajenningsfrankston/NIPS2018_DECAPROP-master","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vanzytay/NIPS2018_DECAPROP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5aac9e872f346e1f47155317f10c88784c56213480c49e8f9845a82db9b51b79","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}