{"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":"/paper/learning-character-level-compositionality","title":"Learning Character-level Compositionality with Visual Features","arxiv_id":"1704.04859","date":"2017-04-17","proceeding":"ACL 2017 7","authors":["Frederick Liu","Han Lu","Chieh Lo","Graham Neubig"],"abstract":"Previous work has modeled the compositionality of words by creating\ncharacter-level models of meaning, reducing problems of sparsity for rare\nwords. However, in many writing systems compositionality has an effect even on\nthe character-level: the meaning of a character is derived by the sum of its\nparts. In this paper, we model this effect by creating embeddings for\ncharacters based on their visual characteristics, creating an image for the\ncharacter and running it through a convolutional neural network to produce a\nvisual character embedding. Experiments on a text classification task\ndemonstrate that such model allows for better processing of instances with rare\ncharacters in languages such as Chinese, Japanese, and Korean. Additionally,\nqualitative analyses demonstrate that our proposed model learns to focus on the\nparts of characters that carry semantic content, resulting in embeddings that\nare coherent in visual space.","url_abs":"http://arxiv.org/abs/1704.04859v2","url_pdf":"http://arxiv.org/pdf/1704.04859v2.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":"learning-character-level-compositionality","repo_url":"https://github.com/frederick0329/Wikipedia_title_dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-character-level-compositionality","repo_url":"https://github.com/IyatomiLab/CE-CLCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[{"slug":"wikipedia-title","name":"Wikipedia Title","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.04859","atlas_url":"https://app.syntology.ai/?focus=1704.04859","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1704.04859"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1704.04859\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1704.04859"},"call":"get_concepts_for_paper(arxiv_id=\"1704.04859\")"}],"by_repo":[{"repo":"frederick0329/Wikipedia_title_dataset","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"IyatomiLab/CE-CLCNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"afce4eb20ff38aa15a2e0c76067456ebec332d4068b36d3439b0aeac5222c239","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}