{"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/phase-conductor-on-multi-layered-attentions","title":"Phase Conductor on Multi-layered Attentions for Machine Comprehension","arxiv_id":"1710.10504","date":"2017-10-28","proceeding":"ICLR 2018 1","authors":["Rui Liu","Wei Wei","Weiguang Mao","Maria Chikina"],"abstract":"Attention models have been intensively studied to improve NLP tasks such as\nmachine comprehension via both question-aware passage attention model and\nself-matching attention model. Our research proposes phase conductor\n(PhaseCond) for attention models in two meaningful ways. First, PhaseCond, an\narchitecture of multi-layered attention models, consists of multiple phases\neach implementing a stack of attention layers producing passage representations\nand a stack of inner or outer fusion layers regulating the information flow.\nSecond, we extend and improve the dot-product attention function for PhaseCond\nby simultaneously encoding multiple question and passage embedding layers from\ndifferent perspectives. We demonstrate the effectiveness of our proposed model\nPhaseCond on the SQuAD dataset, showing that our model significantly\noutperforms both state-of-the-art single-layered and multiple-layered attention\nmodels. We deepen our results with new findings via both detailed qualitative\nanalysis and visualized examples showing the dynamic changes through\nmulti-layered attention models.","url_abs":"http://arxiv.org/abs/1710.10504v2","url_pdf":"http://arxiv.org/pdf/1710.10504v2.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":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Conductor-net (ensemble)","rank_in_archive_order":104,"of":213,"metrics":{"EM":"76.996","F1":"84.630"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Conductor-net (single model)","rank_in_archive_order":128,"of":213,"metrics":{"EM":"74.405","F1":"82.742"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Conductor-net (single)","rank_in_archive_order":138,"of":213,"metrics":{"EM":"73.240","F1":"81.933"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"PhaseCond (single)","rank_in_archive_order":31,"of":55,"metrics":{"EM":"72.1","F1":"81.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d10d1fd3a4046395e0dc64e1c1dcf135872ee7a34c7bbbc89635ce652bf1440d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}