{"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":"/method/content-based-attention","slug":"content-based-attention","name":"Content-based Attention","full_name":"Content-based Attention","full_name_withheld":false,"description_markdown":"**Content-based attention** is an attention mechanism based on cosine similarity:\r\n\r\n$$f_{att}\\left(\\textbf{h}_{i}, \\textbf{s}\\_{j}\\right) = \\cos\\left[\\textbf{h}\\_{i};\\textbf{s}\\_{j}\\right] $$\r\n\r\nIt was utilised in [Neural Turing Machines](https://paperswithcode.com/method/neural-turing-machine) as part of the Addressing Mechanism.\r\n\r\nWe produce a normalized attention weighting by taking a [softmax](https://paperswithcode.com/method/softmax) over these attention alignment scores.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Neural Turing Machines","paper":"/paper/neural-turing-machines","first_author":"Alex Graves","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/neural-turing-machines"},"source":{"url":"http://arxiv.org/abs/1410.5401v2","title":"Neural Turing Machines","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/loudinthecloud/pytorch-ntm/blob/3c64937cb075e737528ff7ecf02b2c1c6d8347a1/ntm/memory.py#L82","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Attention Mechanisms","url":"/methods/category/attention-mechanisms","pwc_aliases":["attention-mechanisms-1"]}],"n_papers_tagged":33,"archive_num_papers":33,"papers_newest_first":[{"paper":null,"slug":"intelligent-dos-and-ddos-detection-a-hybrid","title":"Intelligent DoS and DDoS Detection: A Hybrid GRU-NTM Approach to Network Security","date":"2025-04-10","arxiv_id":"2504.07478","n_code_links":0,"syntology":null},{"paper":"/paper/memory-augmented-conformer-for-improved-end","slug":"memory-augmented-conformer-for-improved-end","title":"Memory-augmented conformer for improved end-to-end long-form ASR","date":"2023-09-22","arxiv_id":"2309.13029","n_code_links":1,"syntology":null},{"paper":null,"slug":"fashionntm-multi-turn-fashion-image-retrieval","title":"FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory","date":"2023-08-20","arxiv_id":"2308.10170","n_code_links":0,"syntology":null},{"paper":"/paper/tps-attention-enhanced-thin-plate-spline-for","slug":"tps-attention-enhanced-thin-plate-spline-for","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","date":"2023-05-09","arxiv_id":"2305.05322","n_code_links":1,"syntology":null},{"paper":"/paper/token-turing-machines","slug":"token-turing-machines","title":"Token Turing Machines","date":"2022-11-16","arxiv_id":"2211.09119","n_code_links":1,"syntology":null},{"paper":null,"slug":"similarity-and-content-based-phonetic-self","title":"Similarity and Content-based Phonetic Self Attention for Speech Recognition","date":"2022-03-19","arxiv_id":"2203.10252","n_code_links":0,"syntology":null},{"paper":null,"slug":"hima-a-fast-and-scalable-history-based-memory","title":"HiMA: A Fast and Scalable History-based Memory Access Engine for Differentiable Neural Computer","date":"2022-02-15","arxiv_id":"2202.07275","n_code_links":0,"syntology":null},{"paper":"/paper/attentionhtr-handwritten-text-recognition","slug":"attentionhtr-handwritten-text-recognition","title":"AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks","date":"2022-01-23","arxiv_id":"2201.09390","n_code_links":1,"syntology":null},{"paper":"/paper/hard-attention-for-scalable-image","slug":"hard-attention-for-scalable-image","title":"Hard-Attention for Scalable Image Classification","date":"2021-02-20","arxiv_id":"2102.10212","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-high-dimensional-memory-augmented","title":"Robust High-dimensional Memory-augmented Neural Networks","date":"2020-10-05","arxiv_id":"2010.01939","n_code_links":0,"syntology":null},{"paper":"/paper/explainable-inference-on-sequential-data-via","slug":"explainable-inference-on-sequential-data-via","title":"Explainable Inference on Sequential Data via Memory-Tracking","date":"2020-07-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-speaker-adaptation-using","title":"Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR","date":"2020-02-14","arxiv_id":"2002.06165","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-to-sequence-singing-synthesis-using","title":"Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer","date":"2019-10-22","arxiv_id":"1910.09989","n_code_links":0,"syntology":null},{"paper":null,"slug":"memory-augmented-recurrent-networks-for","title":"Memory-Augmented Recurrent Networks for Dialogue Coherence","date":"2019-10-16","arxiv_id":"1910.10487","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neural-turingmachine-for-conditional","title":"A Neural Turing~Machine for Conditional Transition Graph Modeling","date":"2019-07-15","arxiv_id":"1907.06432","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-memory-modules-on-learning","title":"Understanding Memory Modules on Learning Simple Algorithms","date":"2019-07-01","arxiv_id":"1907.00820","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-review-on-neural-turing-machine","title":"A review on Neural Turing Machine","date":"2019-04-10","arxiv_id":"1904.05061","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-generalization-across-dialogue-tasks","slug":"few-shot-generalization-across-dialogue-tasks","title":"Few-Shot Generalization Across Dialogue Tasks","date":"2018-11-28","arxiv_id":"1811.11707","n_code_links":2,"syntology":null},{"paper":null,"slug":"context-aware-neural-model-for-temporal","title":"Context-Aware Neural Model for Temporal Information Extraction","date":"2018-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-taxonomy-for-neural-memory-networks","title":"A Taxonomy for Neural Memory Networks","date":"2018-05-01","arxiv_id":"1805.00327","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-set-autoencoder-unsupervised","title":"The Set Autoencoder: Unsupervised Representation Learning for Sets","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-learning-via-feature-label-memory","title":"Meta-Learning via Feature-Label Memory Network","date":"2017-10-19","arxiv_id":"1710.07110","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-attention-using-a-fixed-size-memory","title":"Efficient Attention using a Fixed-Size Memory Representation","date":"2017-07-01","arxiv_id":"1707.00110","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-set-based-metric-learning-for-video","title":"Attention-Set based Metric Learning for Video Face Recognition","date":"2017-04-12","arxiv_id":"1704.03805","n_code_links":0,"syntology":null},{"paper":"/paper/tracking-the-world-state-with-recurrent","slug":"tracking-the-world-state-with-recurrent","title":"Tracking the World State with Recurrent Entity Networks","date":"2016-12-12","arxiv_id":"1612.03969","n_code_links":5,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["facebook/MemNN"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"neural-turing-machines-convergence-of-copy","title":"Neural Turing Machines: Convergence of Copy Tasks","date":"2016-12-07","arxiv_id":"1612.02336","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-cheap-linear-attention-mechanism-with-fast","title":"A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations","date":"2016-09-19","arxiv_id":"1609.05866","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-neural-turing-machine-with-soft-and","slug":"dynamic-neural-turing-machine-with-soft-and","title":"Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes","date":"2016-06-30","arxiv_id":"1607.00036","n_code_links":0,"syntology":null},{"paper":null,"slug":"lie-access-neural-turing-machine","title":"Lie Access Neural Turing Machine","date":"2016-02-28","arxiv_id":"1602.08671","n_code_links":0,"syntology":null},{"paper":null,"slug":"empirical-study-on-deep-learning-models-for","title":"Empirical Study on Deep Learning Models for Question Answering","date":"2015-10-26","arxiv_id":"1510.07526","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-memory-based-architecture-for-sequence","title":"A Deep Memory-based Architecture for Sequence-to-Sequence Learning","date":"2015-06-22","arxiv_id":"1506.06442","n_code_links":0,"syntology":null},{"paper":"/paper/reinforcement-learning-neural-turing-machines","slug":"reinforcement-learning-neural-turing-machines","title":"Reinforcement Learning Neural Turing Machines - Revised","date":"2015-05-04","arxiv_id":"1505.00521","n_code_links":1,"syntology":null},{"paper":"/paper/neural-turing-machines","slug":"neural-turing-machines","title":"Neural Turing Machines","date":"2014-10-20","arxiv_id":"1410.5401","n_code_links":34,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}}],"papers_shown":33,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":33,"with_a_code_link":10,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":33,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/content-based-attention/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/content-based-attention/papers/ran/1","json":"/method/content-based-attention/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/decoder","name":"Decoder","papers":5},{"task":"/task/question-answering","name":"Question Answering","papers":5},{"task":"/task/machine-translation","name":"Machine Translation","papers":3},{"task":"/task/speech-recognition","name":"Speech Recognition","papers":3},{"task":"/task/translation","name":"Translation","papers":3},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":3},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":2},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":2},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":2},{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/information-retrieval","name":"Information Retrieval","papers":2},{"task":"/task/retrieval","name":"Retrieval","papers":2},{"task":"/task/sentence","name":"Sentence","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":"/task/action-detection","name":"Action Detection","papers":1},{"task":"/task/activity-detection","name":"Activity Detection","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/cloze-test","name":"Cloze Test","papers":1},{"task":"/task/common-sense-reasoning","name":"Common Sense Reasoning","papers":1},{"task":"/task/deep-attention","name":"Deep Attention","papers":1}],"tasks_shown":20,"n_tasks":51,"usage_by_year":[{"year":"2014","papers":1},{"year":"2015","papers":3},{"year":"2016","papers":5},{"year":"2017","papers":3},{"year":"2018","papers":4},{"year":"2019","papers":5},{"year":"2020","papers":3},{"year":"2021","papers":1},{"year":"2022","papers":4},{"year":"2023","papers":3},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/content-based-attention"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Content-based%20Attention","read_at":"2026-10-05T00:53:56+00:00","query":"Content-based Attention","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1410.5401","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Content-based Attention' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection","TC-ATTENTION","TF-ATTENTION","EL-Attention","SS-Attention","VC-Attention","Attention-IoU","DFC attention"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"8d1d6afcb6fa223c3c7497d926b10025447a9ca3e3314a96688be390d010b377","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}