{"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/reinforced-self-attention-network-a-hybrid-of","title":"Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling","arxiv_id":"1801.10296","date":"2018-01-31","proceeding":null,"authors":["Tao Shen","Tianyi Zhou","Guodong Long","Jing Jiang","Sen Wang","Chengqi Zhang"],"abstract":"Many natural language processing tasks solely rely on sparse dependencies\nbetween a few tokens in a sentence. Soft attention mechanisms show promising\nperformance in modeling local/global dependencies by soft probabilities between\nevery two tokens, but they are not effective and efficient when applied to long\nsentences. By contrast, hard attention mechanisms directly select a subset of\ntokens but are difficult and inefficient to train due to their combinatorial\nnature. In this paper, we integrate both soft and hard attention into one\ncontext fusion model, \"reinforced self-attention (ReSA)\", for the mutual\nbenefit of each other. In ReSA, a hard attention trims a sequence for a soft\nself-attention to process, while the soft attention feeds reward signals back\nto facilitate the training of the hard one. For this purpose, we develop a\nnovel hard attention called \"reinforced sequence sampling (RSS)\", selecting\ntokens in parallel and trained via policy gradient. Using two RSS modules, ReSA\nefficiently extracts the sparse dependencies between each pair of selected\ntokens. We finally propose an RNN/CNN-free sentence-encoding model, \"reinforced\nself-attention network (ReSAN)\", solely based on ReSA. It achieves\nstate-of-the-art performance on both Stanford Natural Language Inference (SNLI)\nand Sentences Involving Compositional Knowledge (SICK) datasets.","url_abs":"http://arxiv.org/abs/1801.10296v2","url_pdf":"http://arxiv.org/pdf/1801.10296v2.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":"reinforced-self-attention-network-a-hybrid-of","repo_url":"https://github.com/taoshen58/DiSAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"hard-attention","task_name":"Hard Attention"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"300D Reinforced Self-Attention Network","rank_in_archive_order":56,"of":98,"metrics":{"% Test Accuracy":"86.3","% Train Accuracy":"92.6","Parameters":"3.1m"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.10296","atlas_url":"https://app.syntology.ai/?focus=1801.10296","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":"1801.10296"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.10296\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.10296"},"call":"get_concepts_for_paper(arxiv_id=\"1801.10296\")"}],"by_repo":[{"repo":"taoshen58/DiSAN","kind":"official","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":"eb21bd300e55fa3c9f91089b15c44bc543313160adad5eb6875609813d9cb74d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}