{"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/rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","arxiv_id":"2010.12821","date":"2020-10-24","proceeding":"ICLR 2021 1","authors":["Hyung Won Chung","Thibault Févry","Henry Tsai","Melvin Johnson","Sebastian Ruder"],"abstract":"We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to significantly improve the efficiency of parameter allocation in the input embedding of multilingual models. By reallocating the input embedding parameters in the Transformer layers, we achieve dramatically better performance on standard natural language understanding tasks with the same number of parameters during fine-tuning. We also show that allocating additional capacity to the output embedding provides benefits to the model that persist through the fine-tuning stage even though the output embedding is discarded after pre-training. Our analysis shows that larger output embeddings prevent the model's last layers from overspecializing to the pre-training task and encourage Transformer representations to be more general and more transferable to other tasks and languages. Harnessing these findings, we are able to train models that achieve strong performance on the XTREME benchmark without increasing the number of parameters at the fine-tuning stage.","url_abs":"https://arxiv.org/abs/2010.12821v1","url_pdf":"https://arxiv.org/pdf/2010.12821v1.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":"rethinking-embedding-coupling-in-pre-trained-1","repo_url":"https://github.com/Beacontownfc/rembert_paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"rethinking-embedding-coupling-in-pre-trained-1","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/rembert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"rethinking-embedding-coupling-in-pre-trained-1","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-1/rembert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"rethinking-embedding-coupling-in-pre-trained-1","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-3/rembert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"cross-lingual-ner","task_name":"Cross-Lingual NER"},{"task_slug":"cross-lingual-natural-language-inference","task_name":"Cross-Lingual Natural Language Inference"},{"task_slug":"cross-lingual-paraphrase-identification","task_name":"Cross-Lingual Paraphrase Identification"},{"task_slug":"cross-lingual-question-answering","task_name":"Cross-Lingual Question Answering"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-lingual-ner-on-ner","task":"Cross-Lingual NER","dataset":"NER","model":"Coupled","rank_in_archive_order":1,"of":2,"metrics":{"F1":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-ner-on-ner","task":"Cross-Lingual NER","dataset":"NER","model":"Decoupled","rank_in_archive_order":2,"of":2,"metrics":{"F1":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-4","task":"Cross-Lingual Natural Language Inference","dataset":"XNLI","model":"Decoupled","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"71.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-4","task":"Cross-Lingual Natural Language Inference","dataset":"XNLI","model":"Coupled","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"70.7"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-question-answering-on-mlqa","task":"Cross-Lingual Question Answering","dataset":"MLQA","model":"Coupled","rank_in_archive_order":2,"of":3,"metrics":{"EM":"37.3","F1":"53.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-question-answering-on-mlqa","task":"Cross-Lingual Question Answering","dataset":"MLQA","model":"Decoupled","rank_in_archive_order":3,"of":3,"metrics":{"F1":"53.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-question-answering-on-tydiqa","task":"Cross-Lingual Question Answering","dataset":"TyDiQA-GoldP","model":"Decoupled","rank_in_archive_order":8,"of":11,"metrics":{"EM":"42.8","F1":"58.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-question-answering-on-xquad","task":"Cross-Lingual Question Answering","dataset":"XQuAD","model":"Decoupled","rank_in_archive_order":2,"of":4,"metrics":{"EM":"46.9","F1":"63.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-lingual-question-answering-on-xquad","task":"Cross-Lingual Question Answering","dataset":"XQuAD","model":"Coupled","rank_in_archive_order":3,"of":4,"metrics":{"EM":"46.2","F1":"63.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.12821","atlas_url":"https://app.syntology.ai/?focus=2010.12821","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":"2010.12821"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2010.12821\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2010.12821"},"call":"get_concepts_for_paper(arxiv_id=\"2010.12821\")"}],"by_repo":[{"repo":"Beacontownfc/rembert_paddle","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PaddlePaddle/PaddleNLP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.03416"],"harvested_for_calls":[{"arxiv_id":"2301.03416","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.03416"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.03416\")"}]},{"repo":"yangyucheng000/University","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2409.12191"],"harvested_for_calls":[{"arxiv_id":"2409.12191","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2409.12191"},"call":"get_harvested_code_for_paper(arxiv_id=\"2409.12191\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"1c1fbef1e5318eafb6f274360d5ad9b3ec75e37ec086b81934ccdaf161cf60d5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}