{"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/adversarial-decomposition-of-text","title":"Adversarial Decomposition of Text Representation","arxiv_id":"1808.09042","date":"2018-08-27","proceeding":"NAACL 2019 6","authors":["Alexey Romanov","Anna Rumshisky","Anna Rogers","David Donahue"],"abstract":"In this paper, we present a method for adversarial decomposition of text\nrepresentation. This method can be used to decompose a representation of an\ninput sentence into several independent vectors, each of them responsible for a\nspecific aspect of the input sentence. We evaluate the proposed method on two\ncase studies: the conversion between different social registers and diachronic\nlanguage change. We show that the proposed method is capable of fine-grained\ncontrolled change of these aspects of the input sentence. It is also learning a\ncontinuous (rather than categorical) representation of the style of the\nsentence, which is more linguistically realistic. The model uses\nadversarial-motivational training and includes a special motivational loss,\nwhich acts opposite to the discriminator and encourages a better decomposition.\nFurthermore, we evaluate the obtained meaning embeddings on a downstream task\nof paraphrase detection and show that they significantly outperform the\nembeddings of a regular autoencoder.","url_abs":"http://arxiv.org/abs/1808.09042v2","url_pdf":"http://arxiv.org/pdf/1808.09042v2.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":"adversarial-decomposition-of-text","repo_url":"https://github.com/text-machine-lab/adversarial_decomposition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adversarial-decomposition-of-text","repo_url":"https://github.com/B1ackF0X/adversarial_decomposition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.09042","atlas_url":"https://app.syntology.ai/?focus=1808.09042","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":"1808.09042"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1808.09042\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1808.09042"},"call":"get_concepts_for_paper(arxiv_id=\"1808.09042\")"}],"by_repo":[{"repo":"text-machine-lab/adversarial_decomposition","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"B1ackF0X/adversarial_decomposition","kind":"listed","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":"dba5d628a63681f11b4763bda512c66c4eae3cb3e6e94349e7ca8fbc7a462d0d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}