Papers › Cloze-driven Pretraining of Self-attention Networks

Cloze-driven Pretraining of Self-attention Networks

19 Mar 2019IJCNLP 2019 11arXiv:1903.07785archive 2025-07-28

Alexei Baevski, Sergey Edunov, Yinhan Liu, Luke Zettlemoyer, Michael Auli

We present a new approach for pretraining a bi-directional transformer model that provides significant performance gains across a variety of language understanding problems. Our model solves a cloze-style word reconstruction task, where each word is ablated and must be predicted given the rest of the text. Experiments demonstrate large performance gains on GLUE and new state of the art results on NER as well as constituency parsing benchmarks, consistent with the concurrently introduced BERT model. We also present a detailed analysis of a number of factors that contribute to effective pretraining, including data domain and size, model capacity, and variations on the cloze objective.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Constituency ParsingNERNamed Entity Recognition (NER)Sentiment AnalysisText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Constituency Parsing Penn Treebank CNN Large + fine-tune F1 score 95.6 #12 of 27 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) CNN Large + fine-tune F1 93.5 #18 of 73 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification CNN Large Accuracy 94.6 #33 of 87 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 EncodingsAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerWeight DecayWordPiece

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