{"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/cgmh-constrained-sentence-generation-by","title":"CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling","arxiv_id":"1811.10996","date":"2018-11-14","proceeding":null,"authors":["Ning Miao","Hao Zhou","Lili Mou","Rui Yan","Lei LI"],"abstract":"In real-world applications of natural language generation, there are often\nconstraints on the target sentences in addition to fluency and naturalness\nrequirements. Existing language generation techniques are usually based on\nrecurrent neural networks (RNNs). However, it is non-trivial to impose\nconstraints on RNNs while maintaining generation quality, since RNNs generate\nsentences sequentially (or with beam search) from the first word to the last.\nIn this paper, we propose CGMH, a novel approach using Metropolis-Hastings\nsampling for constrained sentence generation. CGMH allows complicated\nconstraints such as the occurrence of multiple keywords in the target\nsentences, which cannot be handled in traditional RNN-based approaches.\nMoreover, CGMH works in the inference stage, and does not require parallel\ncorpora for training. We evaluate our method on a variety of tasks, including\nkeywords-to-sentence generation, unsupervised sentence paraphrasing, and\nunsupervised sentence error correction. CGMH achieves high performance compared\nwith previous supervised methods for sentence generation. Our code is released\nat https://github.com/NingMiao/CGMH","url_abs":"http://arxiv.org/abs/1811.10996v1","url_pdf":"http://arxiv.org/pdf/1811.10996v1.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":"cgmh-constrained-sentence-generation-by","repo_url":"https://github.com/NingMiao/CGMH","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.10996","atlas_url":"https://app.syntology.ai/?focus=1811.10996","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":"1811.10996"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1811.10996\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1811.10996"},"call":"get_concepts_for_paper(arxiv_id=\"1811.10996\")"}],"by_repo":[{"repo":"NingMiao/CGMH","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":"911dc888497e8e4b380e7ce741a6acc6b90e26d59bc300f688acf5298dbe950b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}