{"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/building-language-models-for-text-with-named","title":"Building Language Models for Text with Named Entities","arxiv_id":"1805.04836","date":"2018-05-13","proceeding":"ACL 2018 7","authors":["Md. Rizwan Parvez","Saikat Chakraborty","Baishakhi Ray","Kai-Wei Chang"],"abstract":"Text in many domains involves a significant amount of named entities.\nPredict- ing the entity names is often challenging for a language model as they\nappear less frequent on the training corpus. In this paper, we propose a novel\nand effective approach to building a discriminative language model which can\nlearn the entity names by leveraging their entity type information. We also\nintroduce two benchmark datasets based on recipes and Java programming codes,\non which we evalu- ate the proposed model. Experimental re- sults show that our\nmodel achieves 52.2% better perplexity in recipe generation and 22.06% on code\ngeneration than the state-of-the-art language models.","url_abs":"http://arxiv.org/abs/1805.04836v1","url_pdf":"http://arxiv.org/pdf/1805.04836v1.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":"building-language-models-for-text-with-named","repo_url":"https://github.com/uclanlp/NamedEntityLanguageModel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"building-language-models-for-text-with-named","repo_url":"https://github.com/devanshbatra04/Named-Entity-Language-Models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"recipe-generation","task_name":"Recipe Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-android-repos","task":"Code Generation","dataset":"Android Repos","model":"Entity Type Model","rank_in_archive_order":1,"of":1,"metrics":{"Perplexity":"2.65"},"uses_additional_data":false},{"leaderboard":"/sota/recipe-generation-on-now-youre-cooking","task":"Recipe Generation","dataset":"Now You're Cooking!","model":"Entity Type Model","rank_in_archive_order":2,"of":2,"metrics":{"Perplexity":"9.67"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.04836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.04836"}},"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/uclanlp/NamedEntityLanguageModel","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/devanshbatra04/Named-Entity-Language-Models","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"3c2fe307e011be7d","entry":"embedded_dropout","repo":"uclanlp/NamedEntityLanguageModel","repo_kind":"official","path":"embed_regularize.py","file_url":"https://github.com/uclanlp/NamedEntityLanguageModel/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":"3c2fe307e011be7d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}