{"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-to-compute-word-embeddings-on-the","title":"Learning to Compute Word Embeddings On the Fly","arxiv_id":"1706.00286","date":"2017-06-01","proceeding":"ICLR 2018 1","authors":["Dzmitry Bahdanau","Tom Bosc","Stanisław Jastrzębski","Edward Grefenstette","Pascal Vincent","Yoshua Bengio"],"abstract":"Words in natural language follow a Zipfian distribution whereby some words\nare frequent but most are rare. Learning representations for words in the \"long\ntail\" of this distribution requires enormous amounts of data. Representations\nof rare words trained directly on end tasks are usually poor, requiring us to\npre-train embeddings on external data, or treat all rare words as\nout-of-vocabulary words with a unique representation. We provide a method for\npredicting embeddings of rare words on the fly from small amounts of auxiliary\ndata with a network trained end-to-end for the downstream task. We show that\nthis improves results against baselines where embeddings are trained on the end\ntask for reading comprehension, recognizing textual entailment and language\nmodeling.","url_abs":"http://arxiv.org/abs/1706.00286v3","url_pdf":"http://arxiv.org/pdf/1706.00286v3.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":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"OTF dict+spelling (single)","rank_in_archive_order":183,"of":213,"metrics":{"EM":"64.083","F1":"73.056"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"OTF spelling (single)","rank_in_archive_order":185,"of":213,"metrics":{"EM":"62.897","F1":"72.016"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"OTF spelling+lemma (single)","rank_in_archive_order":186,"of":213,"metrics":{"EM":"62.604","F1":"71.968"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"OTF dict+spelling (single)","rank_in_archive_order":48,"of":55,"metrics":{"EM":"63.06"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.00286","atlas_url":"https://app.syntology.ai/?focus=1706.00286","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":"1706.00286"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1706.00286\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1706.00286"},"call":"get_concepts_for_paper(arxiv_id=\"1706.00286\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"41088cb80e78e6257e0894e96475bd5abb8532f440a720597f0c9b371804d68b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}