{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/tracking-the-world-state-with-recurrent","title":"Tracking the World State with Recurrent Entity Networks","arxiv_id":"1612.03969","date":"2016-12-12","proceeding":null,"authors":["Mikael Henaff","Jason Weston","Arthur Szlam","Antoine Bordes","Yann Lecun"],"abstract":"We introduce a new model, the Recurrent Entity Network (EntNet). It is\nequipped with a dynamic long-term memory which allows it to maintain and update\na representation of the state of the world as it receives new data. For\nlanguage understanding tasks, it can reason on-the-fly as it reads text, not\njust when it is required to answer a question or respond as is the case for a\nMemory Network (Sukhbaatar et al., 2015). Like a Neural Turing Machine or\nDifferentiable Neural Computer (Graves et al., 2014; 2016) it maintains a fixed\nsize memory and can learn to perform location and content-based read and write\noperations. However, unlike those models it has a simple parallel architecture\nin which several memory locations can be updated simultaneously. The EntNet\nsets a new state-of-the-art on the bAbI tasks, and is the first method to solve\nall the tasks in the 10k training examples setting. We also demonstrate that it\ncan solve a reasoning task which requires a large number of supporting facts,\nwhich other methods are not able to solve, and can generalize past its training\nhorizon. It can also be practically used on large scale datasets such as\nChildren's Book Test, where it obtains competitive performance, reading the\nstory in a single pass.","url_abs":"http://arxiv.org/abs/1612.03969v3","url_pdf":"http://arxiv.org/pdf/1612.03969v3.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":"tracking-the-world-state-with-recurrent","repo_url":"https://github.com/facebook/MemNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"tracking-the-world-state-with-recurrent","repo_url":"https://github.com/akshathaarodi/textual_timetravel_tom","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"tracking-the-world-state-with-recurrent","repo_url":"https://github.com/hsakas/Recurrent-Entity-Network-EntNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"tracking-the-world-state-with-recurrent","repo_url":"https://github.com/jimfleming/recurrent-entity-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"tracking-the-world-state-with-recurrent","repo_url":"https://github.com/siddk/entity-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"procedural-text-understanding","task_name":"Procedural Text Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"content-based-attention","method_name":"Content-based Attention"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"location-based-attention","method_name":"Location-based Attention"},{"method_slug":"neural-turing-machine","method_name":"Neural Turing Machine"},{"method_slug":"recurrent-entity-network","method_name":"Recurrent Entity Network"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"recurrent-entity-network","name":"Recurrent Entity Network","full_name":"Recurrent Entity Network"}],"results":[{"leaderboard":"/sota/question-answering-on-babi","task":"Question Answering","dataset":"bAbi","model":"EntNet","rank_in_archive_order":3,"of":14,"metrics":{"Accuracy (trained on 10k)":"99.5%","Accuracy (trained on 1k)":"89.1%","Mean Error Rate":"9.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.03969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.03969"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/siddk/entity-network","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jimfleming/recurrent-entity-networks","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hsakas/Recurrent-Entity-Network-EntNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebook/MemNN","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/akshathaarodi/textual_timetravel_tom","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7c074f00ba51e7e9","entry":"parse_stories","repo":"jimfleming/recurrent-entity-networks","repo_kind":"listed","path":"entity_networks/prep_data.py","file_url":"https://github.com/jimfleming/recurrent-entity-networks/blob/HEAD/entity_networks/prep_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c074f00ba51e7e9"}},{"code_sha256_prefix":"118f16bd1bc27cd3","entry":"tokenize","repo":"jimfleming/recurrent-entity-networks","repo_kind":"listed","path":"entity_networks/prep_data.py","file_url":"https://github.com/jimfleming/recurrent-entity-networks/blob/HEAD/entity_networks/prep_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"118f16bd1bc27cd3"}},{"code_sha256_prefix":"f3e927bfb1e03638","entry":"tokenize_stories","repo":"jimfleming/recurrent-entity-networks","repo_kind":"listed","path":"entity_networks/prep_data.py","file_url":"https://github.com/jimfleming/recurrent-entity-networks/blob/HEAD/entity_networks/prep_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3e927bfb1e03638"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}