{"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/feature-adaptation-of-pre-trained-language","title":"Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training","arxiv_id":"2009.11538","date":"2020-09-24","proceeding":"EMNLP 2020 11","authors":["Hai Ye","Qingyu Tan","Ruidan He","Juntao Li","Hwee Tou Ng","Lidong Bing"],"abstract":"Adapting pre-trained language models (PrLMs) (e.g., BERT) to new domains has gained much attention recently. Instead of fine-tuning PrLMs as done in most previous work, we investigate how to adapt the features of PrLMs to new domains without fine-tuning. We explore unsupervised domain adaptation (UDA) in this paper. With the features from PrLMs, we adapt the models trained with labeled data from the source domain to the unlabeled target domain. Self-training is widely used for UDA which predicts pseudo labels on the target domain data for training. However, the predicted pseudo labels inevitably include noise, which will negatively affect training a robust model. To improve the robustness of self-training, in this paper we present class-aware feature self-distillation (CFd) to learn discriminative features from PrLMs, in which PrLM features are self-distilled into a feature adaptation module and the features from the same class are more tightly clustered. We further extend CFd to a cross-language setting, in which language discrepancy is studied. Experiments on two monolingual and multilingual Amazon review datasets show that CFd can consistently improve the performance of self-training in cross-domain and cross-language settings.","url_abs":"https://arxiv.org/abs/2009.11538v3","url_pdf":"https://arxiv.org/pdf/2009.11538v3.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":"feature-adaptation-of-pre-trained-language","repo_url":"https://github.com/oceanypt/CFd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"feature-adaptation-of-pre-trained-language","repo_url":"https://github.com/AntheaLi/cs224nProject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.11538","atlas_url":"https://app.syntology.ai/?focus=2009.11538","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":"2009.11538"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2009.11538\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2009.11538"},"call":"get_concepts_for_paper(arxiv_id=\"2009.11538\")"}],"by_repo":[{"repo":"oceanypt/CFd","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"AntheaLi/cs224nProject","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":"05efc54cb593263a5f84a289f477fad848de6c2b170e15520807d9edef1633c3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}