{"url":"/method/pointer-net","slug":"pointer-net","name":"Pointer Network","full_name":"Pointer Network","full_name_withheld":false,"description_markdown":"**Pointer Networks** tackle problems where input and output data are sequential data, but can't be solved by seq2seq type models because discrete categories of output elements depend on the variable input size (and are not decided in advance).\r\n\r\nA Pointer Network learns the conditional  probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. They solve the problem of variable size output dictionaries using [additive attention](https://paperswithcode.com/method/additive-attention). But instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, Pointer Networks use attention as a pointer to select a member of the input sequence as the output. \r\n\r\nPointer-Nets can be used to learn approximate solutions to challenging geometric problems such as finding planar convex hulls, computing Delaunay triangulations, and the planar Travelling Salesman Problem.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Pointer Networks","paper":"/paper/pointer-networks","first_author":"Oriol Vinyals","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pointer-networks"},"source":{"url":"http://arxiv.org/abs/1506.03134v2","title":"Pointer Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Sequential","area_id":"sequential","collection":"Recurrent Neural Networks","url":"/methods/category/recurrent-neural-networks","pwc_aliases":[]},{"area":"Sequential","area_id":"sequential","collection":"Sequence To Sequence Models","url":"/methods/category/sequence-to-sequence-models","pwc_aliases":[]}],"n_papers_tagged":105,"archive_num_papers":105,"papers_newest_first":[{"paper":"/paper/pointer-guided-pre-training-infusing-large","title":"Pointer-Guided Pre-Training: Infusing Large Language Models with Paragraph-Level Contextual Awareness","date":"2024-06-06","arxiv_id":"2406.04156","n_code_links":1,"syntology":null},{"paper":null,"title":"Solving the QAP by Two-Stage Graph Pointer Networks and Reinforcement Learning","date":"2024-03-31","arxiv_id":"2404.00539","n_code_links":0,"syntology":null},{"paper":"/paper/self-labeling-the-job-shop-scheduling-problem","title":"Self-Labeling the Job Shop Scheduling Problem","date":"2024-01-22","arxiv_id":"2401.11849","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":2}},{"paper":"/paper/large-language-models-play-starcraft-ii","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","date":"2023-12-19","arxiv_id":"2312.11865","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":null,"title":"End-to-End real time tracking of children's reading with pointer network","date":"2023-10-17","arxiv_id":"2310.11486","n_code_links":0,"syntology":null},{"paper":null,"title":"A Robust and Opponent-Aware League Training Method for StarCraft II","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/alphastar-unplugged-large-scale-offline","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","date":"2023-08-07","arxiv_id":"2308.03526","n_code_links":1,"syntology":{"ran":4,"of":4,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets","date":"2023-07-11","arxiv_id":"2307.05641","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning to Branch in Combinatorial Optimization with Graph Pointer Networks","date":"2023-07-04","arxiv_id":"2307.01434","n_code_links":0,"syntology":null},{"paper":"/paper/rl4co-an-extensive-reinforcement-learning-for","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","date":"2023-06-29","arxiv_id":"2306.17100","n_code_links":3,"syntology":{"ran":0,"of":16,"unverified":16,"pointer_only":3}},{"paper":"/paper/towards-accurate-translation-via-semantically","title":"Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints","date":"2023-06-21","arxiv_id":"2306.12089","n_code_links":1,"syntology":null},{"paper":null,"title":"Structured Sentiment Analysis as Transition-based Dependency Parsing","date":"2023-05-09","arxiv_id":"2305.05311","n_code_links":0,"syntology":null},{"paper":"/paper/pk-chat-pointer-network-guided-knowledge","title":"PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model","date":"2023-04-02","arxiv_id":"2304.00592","n_code_links":2,"syntology":null},{"paper":null,"title":"Coordinating CAV Swarms at Intersections with a Deep Learning Model","date":"2022-11-10","arxiv_id":"2211.05297","n_code_links":0,"syntology":null},{"paper":null,"title":"Accelerating the Genetic Algorithm for Large-scale Traveling Salesman Problems by Cooperative Coevolutionary Pointer Network with Reinforcement Learning","date":"2022-09-27","arxiv_id":"2209.13077","n_code_links":0,"syntology":null},{"paper":"/paper/on-efficient-reinforcement-learning-for-full","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","date":"2022-09-23","arxiv_id":"2209.11553","n_code_links":2,"syntology":{"ran":0,"of":10,"unverified":10,"pointer_only":0}},{"paper":"/paper/modeling-user-repeat-consumption-behavior-for","title":"Modeling User Repeat Consumption Behavior for Online Novel Recommendation","date":"2022-09-05","arxiv_id":"2209.01963","n_code_links":1,"syntology":null},{"paper":null,"title":"Deep Reinforcement Learning for Orienteering Problems Based on Decomposition","date":"2022-04-25","arxiv_id":"2204.11575","n_code_links":0,"syntology":null},{"paper":"/paper/multi-objective-pointer-network-for","title":"Multi-objective Pointer Network for Combinatorial Optimization","date":"2022-04-25","arxiv_id":"2204.11860","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":2}},{"paper":"/paper/fix-bugs-with-transformer-through-a-neural-1","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2022-04-13","arxiv_id":"2204.06643","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-pairwise-mutual-information-for","title":"Exploiting Pairwise Mutual Information for Knowledge-Grounded Dialogue","date":"2022-03-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/neural-face-identification-in-a-2d-wireframe-1","title":"Neural Face Identification in a 2D Wireframe Projection of a Manifold Object","date":"2022-03-08","arxiv_id":"2203.04229","n_code_links":1,"syntology":{"ran":6,"of":9,"unverified":3,"pointer_only":0}},{"paper":null,"title":"A Data-Driven Column Generation Algorithm For Bin Packing Problem in Manufacturing Industry","date":"2022-02-25","arxiv_id":"2202.12466","n_code_links":0,"syntology":null},{"paper":"/paper/towards-personalized-answer-generation-in-e","title":"Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling","date":"2021-12-27","arxiv_id":"2112.13556","n_code_links":1,"syntology":null},{"paper":"/paper/attention-based-model-and-deep-reinforcement","title":"Attention-Based Model and Deep Reinforcement Learning for Distribution of Event Processing Tasks","date":"2021-12-07","arxiv_id":"2112.03835","n_code_links":1,"syntology":null},{"paper":null,"title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"QA4PRF: A Question Answering based Framework for Pseudo Relevance Feedback","date":"2021-11-16","arxiv_id":"2111.08229","n_code_links":0,"syntology":null},{"paper":null,"title":"AI in Human-computer Gaming: Techniques, Challenges and Opportunities","date":"2021-11-15","arxiv_id":"2111.07631","n_code_links":0,"syntology":null},{"paper":null,"title":"A Copy-Augmented Generative Model for Open-Domain Question Answering","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-pointer-networks-for-traveling","title":"Hybrid Pointer Networks for Traveling Salesman Problems Optimization","date":"2021-10-06","arxiv_id":"2110.03104","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":15},{"task":"/task/sentence","name":"Sentence","papers":15},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":15},{"task":"/task/combinatorial-optimization","name":"Combinatorial Optimization","papers":14},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":14},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":12},{"task":"/task/language-modelling","name":"Language Modelling","papers":8},{"task":"/task/question-answering","name":"Question Answering","papers":7},{"task":"/task/starcraft-ii","name":"Starcraft II","papers":7},{"task":"/task/decoder","name":"Decoder","papers":6},{"task":"/task/language-modeling","name":"Language Modeling","papers":6},{"task":"/task/starcraft","name":"Starcraft","papers":6},{"task":"/task/text-generation","name":"Text Generation","papers":5},{"task":"/task/traveling-salesman-problem","name":"Traveling Salesman Problem","papers":5},{"task":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization","papers":4},{"task":"/task/dialogue-state-tracking","name":"Dialogue State Tracking","papers":4},{"task":"/task/diversity","name":"Diversity","papers":4},{"task":"/task/document-summarization","name":"Document Summarization","papers":4},{"task":"/task/knowledge-graphs","name":"Knowledge Graphs","papers":4},{"task":null,"name":"Relation","papers":4}],"tasks_shown":20,"n_tasks":136,"usage_by_year":[{"year":"2015","papers":1},{"year":"2016","papers":3},{"year":"2017","papers":1},{"year":"2018","papers":6},{"year":"2019","papers":21},{"year":"2020","papers":22},{"year":"2021","papers":28},{"year":"2022","papers":10},{"year":"2023","papers":10},{"year":"2024","papers":3}],"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/pointer-net"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}