Papers › Unified Language Model Pre-training for Natural Language Understanding and Generation

Unified Language Model Pre-training for Natural Language Understanding and Generation

8 May 2019NeurIPS 2019 12arXiv:1905.03197archive 2025-07-28

Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieves new state-of-the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40.51 (2.04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35.75 (0.86 absolute improvement), the CoQA generative question answering F1 score to 82.5 (37.1 absolute improvement), the SQuAD question generation BLEU-4 to 22.12 (3.75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2.67 (human performance is 2.65). The code and pre-trained models are available at https://github.com/microsoft/unilm.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

microsoft/unilm officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training (arXiv:2002.12804; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified), DeepNet: Scaling Transformers to 1,000 Layers (arXiv:2203.00555; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
KnightZhang625/BERT_TF mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
LeonZh0u/Chatbot mentioned on GitHubpytorchSyntology: not harvested report
YunwenTechnology/Unilm mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/data2vec_vision mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
jiaruncao/BioCopyMechanism mentioned on GitHubSyntology: not harvested report
robinsongh381/unilm_pytorch_korean mentioned on GitHubpytorchSyntology: not harvested report
uabinf/nlp-fall-2019-project-anuradha_shinjitha mentioned on GitHubSyntology: not harvested report
fuqiang-git-hub/unilmv1-Paddle paddleSyntology: not harvested report

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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Abstractive Text SummarizationDocument SummarizationGenerative Question AnsweringLanguage ModelingLanguage ModellingNatural Language UnderstandingQuestion AnsweringQuestion GenerationQuestion-GenerationResponse GenerationText GenerationText Summarization

Datasets

Introduced by this paper, per the archive.

Liu et al. Corpus

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail UniLM ROUGE-1 43.08 #25 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail UniLM ROUGE-2 20.43 #25 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail UniLM ROUGE-L 40.34 #25 of 53 Archive leaderboard report
Document Summarization CNN / Daily Mail UniLM (Abstractive Summarization) ROUGE-1 43.08 #13 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail UniLM (Abstractive Summarization) ROUGE-2 20.43 #13 of 26 Archive leaderboard report
Document Summarization CNN / Daily Mail UniLM (Abstractive Summarization) ROUGE-L 40.34 #13 of 26 Archive leaderboard report
Generative Question Answering CoQA UniLM F1-Score 82.5 #2 of 3 Archive leaderboard report
Question Generation SQuAD1.1 UniLM BLEU-4 22.78 #8 of 13 Archive leaderboard report
Question Generation SQuAD1.1 UniLM METEOR 25.1 #8 of 13 Archive leaderboard report
Question Generation SQuAD1.1 UniLM ROUGE-L 51.1 #8 of 13 Archive leaderboard report
Text Summarization GigaWord UniLM ROUGE-1 38.90 #18 of 41 Archive leaderboard report
Text Summarization GigaWord UniLM ROUGE-2 20.05 #18 of 41 Archive leaderboard report
Text Summarization GigaWord UniLM ROUGE-L 36.00 #18 of 41 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