{"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/representations-of-language-in-a-model-of","title":"Representations of language in a model of visually grounded speech signal","arxiv_id":"1702.01991","date":"2017-02-07","proceeding":"ACL 2017 7","authors":["Grzegorz Chrupała","Lieke Gelderloos","Afra Alishahi"],"abstract":"We present a visually grounded model of speech perception which projects\nspoken utterances and images to a joint semantic space. We use a multi-layer\nrecurrent highway network to model the temporal nature of spoken speech, and\nshow that it learns to extract both form and meaning-based linguistic knowledge\nfrom the input signal. We carry out an in-depth analysis of the representations\nused by different components of the trained model and show that encoding of\nsemantic aspects tends to become richer as we go up the hierarchy of layers,\nwhereas encoding of form-related aspects of the language input tends to\ninitially increase and then plateau or decrease.","url_abs":"http://arxiv.org/abs/1702.01991v3","url_pdf":"http://arxiv.org/pdf/1702.01991v3.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":"representations-of-language-in-a-model-of","repo_url":"https://github.com/gchrupala/visually-grounded-speech","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"representations-of-language-in-a-model-of","repo_url":"https://github.com/William-N-Havard/VGS-dataset-metadata","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"form","task_name":"Form"}],"methods":[{"method_slug":"highway-layer","method_name":"Highway Layer"},{"method_slug":"highway-network","method_name":"Highway Network"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.01991","atlas_url":"https://app.syntology.ai/?focus=1702.01991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.01991"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/gchrupala/visually-grounded-speech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/William-N-Havard/VGS-dataset-metadata","reach":{"status":"unanswered"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"311b8a8857ac1bba","entry":"characters","repo":"gchrupala/visually-grounded-speech","repo_kind":"official","path":"imaginet/simple_data.py","file_url":"https://github.com/gchrupala/visually-grounded-speech/blob/HEAD/imaginet/simple_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":"311b8a8857ac1bba"}},{"code_sha256_prefix":"bf53b8403698f196","entry":"compressed","repo":"gchrupala/visually-grounded-speech","repo_kind":"official","path":"imaginet/simple_data.py","file_url":"https://github.com/gchrupala/visually-grounded-speech/blob/HEAD/imaginet/simple_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":"bf53b8403698f196"}},{"code_sha256_prefix":"59be76278057b936","entry":"getDataProvider","repo":"gchrupala/visually-grounded-speech","repo_kind":"official","path":"imaginet/data_provider.py","file_url":"https://github.com/gchrupala/visually-grounded-speech/blob/HEAD/imaginet/data_provider.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":"59be76278057b936"}},{"code_sha256_prefix":"1e97b6807aade707","entry":"synthesized","repo":"gchrupala/visually-grounded-speech","repo_kind":"official","path":"analysis/extract_sick_features.py","file_url":"https://github.com/gchrupala/visually-grounded-speech/blob/HEAD/analysis/extract_sick_features.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":"1e97b6807aade707"}},{"code_sha256_prefix":"2cb402342d8b5ded","entry":"words","repo":"gchrupala/visually-grounded-speech","repo_kind":"official","path":"imaginet/simple_data.py","file_url":"https://github.com/gchrupala/visually-grounded-speech/blob/HEAD/imaginet/simple_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":"2cb402342d8b5ded"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}