Papers › Rethinking embedding coupling in pre-trained language models

Rethinking embedding coupling in pre-trained language models

24 Oct 2020ICLR 2021 1arXiv:2010.12821archive 2025-07-28

Hyung Won Chung, Thibault Févry, Henry Tsai, Melvin Johnson, Sebastian Ruder

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Lingual NERCross-Lingual Natural Language InferenceCross-Lingual Paraphrase IdentificationCross-Lingual Question AnsweringNamed Entity Recognition (NER)Natural Language Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Lingual NER NER Coupled F1 69.2 #1 of 2 Archive leaderboard report
Cross-Lingual NER NER Decoupled F1 68.9 #2 of 2 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI Decoupled Accuracy 71.3 #2 of 5 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI Coupled Accuracy 70.7 #3 of 5 Archive leaderboard report
Cross-Lingual Question Answering MLQA Coupled EM 37.3 #2 of 3 Archive leaderboard report
Cross-Lingual Question Answering MLQA Coupled F1 53.1 #2 of 3 Archive leaderboard report
Cross-Lingual Question Answering MLQA Decoupled F1 53.1 #3 of 3 Archive leaderboard report
Cross-Lingual Question Answering TyDiQA-GoldP Decoupled EM 42.8 #8 of 11 Archive leaderboard report
Cross-Lingual Question Answering TyDiQA-GoldP Decoupled F1 58.1 #8 of 11 Archive leaderboard report
Cross-Lingual Question Answering XQuAD Decoupled EM 46.9 #2 of 4 Archive leaderboard report
Cross-Lingual Question Answering XQuAD Decoupled F1 63.8 #2 of 4 Archive leaderboard report
Cross-Lingual Question Answering XQuAD Coupled EM 46.2 #3 of 4 Archive leaderboard report
Cross-Lingual Question Answering XQuAD Coupled F1 63.2 #3 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections