{"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/gile-a-generalized-input-label-embedding-for","title":"GILE: A Generalized Input-Label Embedding for Text Classification","arxiv_id":"1806.06219","date":"2018-06-16","proceeding":"TACL 2019 3","authors":["Nikolaos Pappas","James Henderson"],"abstract":"Neural text classification models typically treat output labels as\ncategorical variables which lack description and semantics. This forces their\nparametrization to be dependent on the label set size, and, hence, they are\nunable to scale to large label sets and generalize to unseen ones. Existing\njoint input-label text models overcome these issues by exploiting label\ndescriptions, but they are unable to capture complex label relationships, have\nrigid parametrization, and their gains on unseen labels happen often at the\nexpense of weak performance on the labels seen during training. In this paper,\nwe propose a new input-label model which generalizes over previous such models,\naddresses their limitations and does not compromise performance on seen labels.\nThe model consists of a joint non-linear input-label embedding with\ncontrollable capacity and a joint-space-dependent classification unit which is\ntrained with cross-entropy loss to optimize classification performance. We\nevaluate models on full-resource and low- or zero-resource text classification\nof multilingual news and biomedical text with a large label set. Our model\noutperforms monolingual and multilingual models which do not leverage label\nsemantics and previous joint input-label space models in both scenarios.","url_abs":"http://arxiv.org/abs/1806.06219v3","url_pdf":"http://arxiv.org/pdf/1806.06219v3.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":"gile-a-generalized-input-label-embedding-for","repo_url":"https://github.com/idiap/gile","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.06219","atlas_url":"https://app.syntology.ai/?focus=1806.06219","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":"1806.06219"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1806.06219\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1806.06219"},"call":"get_concepts_for_paper(arxiv_id=\"1806.06219\")"}],"by_repo":[{"repo":"idiap/gile","kind":"official","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":"169cb4e148f8fc0b7c48ac9d713d8060d95cf4ceaffdf831db9ac72412a7a009","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}