{"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/unsupervised-discovery-of-multimodal-links-in","title":"Unsupervised Discovery of Multimodal Links in Multi-image, Multi-sentence Documents","arxiv_id":"1904.07826","date":"2019-04-16","proceeding":"IJCNLP 2019 11","authors":["Jack Hessel","Lillian Lee","David Mimno"],"abstract":"Images and text co-occur constantly on the web, but explicit links between images and sentences (or other intra-document textual units) are often not present. We present algorithms that discover image-sentence relationships without relying on explicit multimodal annotation in training. We experiment on seven datasets of varying difficulty, ranging from documents consisting of groups of images captioned post hoc by crowdworkers to naturally-occurring user-generated multimodal documents. We find that a structured training objective based on identifying whether collections of images and sentences co-occur in documents can suffice to predict links between specific sentences and specific images within the same document at test time.","url_abs":"https://arxiv.org/abs/1904.07826v2","url_pdf":"https://arxiv.org/pdf/1904.07826v2.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":"unsupervised-discovery-of-multimodal-links-in","repo_url":"https://github.com/jmhessel/multi-retrieval","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"unsupervised-discovery-of-multimodal-links-in","repo_url":"https://github.com/gyauney/domain-specific-lexical-grounding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.07826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07826"}},"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/jmhessel/multi-retrieval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gyauney/domain-specific-lexical-grounding","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"003096f93091757e","entry":"load_data","repo":"jmhessel/multi-retrieval","repo_kind":"official","path":"train_doc.py","file_url":"https://github.com/jmhessel/multi-retrieval/blob/HEAD/train_doc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"003096f93091757e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}