{"doi":"10.18653/v1/d19-1633","title":"Mask-Predict: Parallel Decoding of Conditional Masked Language Models","abstract":"Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation. This approach allows for efficient iterative decoding, where we first predict all of the target words non-autoregressively, and then repeatedly mask out and regenerate the subset of words that the model is least confident about. By applying this strategy for a constant number of iterations, our model improves state-of-the-art performance levels for non-autoregressive and parallel decoding translation models by over 4 BLEU on average. It is also able to reach within about 1 BLEU point of a typical left-to-right transformer model, while decoding significantly faster.","journal":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","year":2019,"id":10358,"datarank":0.7814229229262133,"base_score":5.209486152841421,"endowment":5.209486152841421,"self_citation_contribution":0.7814229229262133,"citation_network_contribution":0.0,"self_endowment_contribution":0.7814229229262133,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":182,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.0476,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2019-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":86663,"name":"Omer Levy","orcid":"0000-0001-7300-8191","position":1,"is_corresponding":false},{"id":86664,"name":"Yinhan Liu","orcid":null,"position":2,"is_corresponding":false},{"id":86665,"name":"Luke Zettlemoyer","orcid":"0009-0008-8296-0764","position":3,"is_corresponding":false},{"id":86662,"name":"Marjan Ghazvininejad","orcid":null,"position":0,"is_corresponding":true}],"reference_count":19,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}