{"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/spell-once-summon-anywhere-a-two-level-open","title":"Spell Once, Summon Anywhere: A Two-Level Open-Vocabulary Language Model","arxiv_id":"1804.08205","date":"2018-04-23","proceeding":null,"authors":["Sabrina J. Mielke","Jason Eisner"],"abstract":"We show how the spellings of known words can help us deal with unknown words in open-vocabulary NLP tasks. The method we propose can be used to extend any closed-vocabulary generative model, but in this paper we specifically consider the case of neural language modeling. Our Bayesian generative story combines a standard RNN language model (generating the word tokens in each sentence) with an RNN-based spelling model (generating the letters in each word type). These two RNNs respectively capture sentence structure and word structure, and are kept separate as in linguistics. By invoking the second RNN to generate spellings for novel words in context, we obtain an open-vocabulary language model. For known words, embeddings are naturally inferred by combining evidence from type spelling and token context. Comparing to baselines (including a novel strong baseline), we beat previous work and establish state-of-the-art results on multiple datasets.","url_abs":"https://arxiv.org/abs/1804.08205v4","url_pdf":"https://arxiv.org/pdf/1804.08205v4.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":"spell-once-summon-anywhere-a-two-level-open","repo_url":"https://github.com/sjmielke/spell-once","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.08205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.08205"}},"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/sjmielke/spell-once","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"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":"4d7f0358b6e7da28","entry":"batchify","repo":"sjmielke/spell-once","repo_kind":"official","path":"utils.py","file_url":"https://github.com/sjmielke/spell-once/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4d7f0358b6e7da28"}},{"code_sha256_prefix":"85281b50c86cffc8","entry":"embedded_dropout","repo":"sjmielke/spell-once","repo_kind":"official","path":"embed_regularize.py","file_url":"https://github.com/sjmielke/spell-once/blob/HEAD/embed_regularize.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"85281b50c86cffc8"}},{"code_sha256_prefix":"dda59cff118690c4","entry":"openfile","repo":"sjmielke/spell-once","repo_kind":"official","path":"data.py","file_url":"https://github.com/sjmielke/spell-once/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dda59cff118690c4"}},{"code_sha256_prefix":"626ebcbda1b6e336","entry":"repackage_hidden","repo":"sjmielke/spell-once","repo_kind":"official","path":"utils.py","file_url":"https://github.com/sjmielke/spell-once/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"626ebcbda1b6e336"}},{"code_sha256_prefix":"4670a51fb38974ff","entry":"sentence_batchify","repo":"sjmielke/spell-once","repo_kind":"official","path":"utils.py","file_url":"https://github.com/sjmielke/spell-once/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4670a51fb38974ff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}