Papers › Semantics-aware BERT for Language Understanding

Semantics-aware BERT for Language Understanding

5 Sep 2019arXiv:1909.02209archive 2025-07-28

Zhuosheng Zhang, Yuwei Wu, Hai Zhao, Zuchao Li, Shuailiang Zhang, Xi Zhou, Xiang Zhou

The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks. However, the existing language representation models including ELMo, GPT and BERT only exploit plain context-sensitive features such as character or word embeddings. They rarely consider incorporating structured semantic information which can provide rich semantics for language representation. To promote natural language understanding, we propose to incorporate explicit contextual semantics from pre-trained semantic role labeling, and introduce an improved language representation model, Semantics-aware BERT (SemBERT), which is capable of explicitly absorbing contextual semantics over a BERT backbone. SemBERT keeps the convenient usability of its BERT precursor in a light fine-tuning way without substantial task-specific modifications. Compared with BERT, semantics-aware BERT is as simple in concept but more powerful. It obtains new state-of-the-art or substantially improves results on ten reading comprehension and language inference tasks.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1909.02209")

Code

Syntology Ran 4 of 12 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong.

By repository: official repository: 12 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cooelf/SemBERT officialpytorchMIT 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.

Code Syntology ran Syntology

12 samples harvested; 4 ran; 2 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
8unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cooelf/SemBERT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

swish cooelf/SemBERT/pytorch_pretrained_bert/modeling.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report
accuracy cooelf/SemBERT/run_scorer.py official repository ran · honoured contract fingerprinted MIT (permissive) · eb725d5794b15f6b · report
gelu cooelf/SemBERT/pytorch_pretrained_bert/modeling.py official repository ran · honoured contract fingerprinted MIT (permissive) · fdc64f4c72036ae4 · report
url_to_filename cooelf/SemBERT/pytorch_pretrained_bert/file_utils.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5eff22fa0a651276 · report
cached_path cooelf/SemBERT/pytorch_pretrained_bert/file_utils.py official repository unverified MIT (permissive) · df9f10631fa5d322 · report
detokenize cooelf/SemBERT/data_process/util.py official repository unverified MIT (permissive) · 517a71720243fbf7 · report
filename_to_url cooelf/SemBERT/pytorch_pretrained_bert/file_utils.py official repository unverified MIT (permissive) · 6db16fe8f67e56b6 · report
get_tags cooelf/SemBERT/tag_model/tagging.py official repository unverified MIT (permissive) · 99e01374e3f7e24f · report
load_tag_vocab cooelf/SemBERT/tag_model/tag_tokenization.py official repository unverified MIT (permissive) · ebe8bc8fe2ec06d1 · report
load_tf_weights_in_bert cooelf/SemBERT/pytorch_pretrained_bert/modeling.py official repository unverified MIT (permissive) · baa5766f4566aafc · report
transform_tag_features cooelf/SemBERT/run_scorer.py official repository unverified MIT (permissive) · 5101ed51dc95ac5e · report
transform_tag_features cooelf/SemBERT/run_classifier.py official repository unverified MIT (permissive) · bdddb1a2d67bc868 · report

Tasks

Language ModelingLanguage ModellingMachine Reading ComprehensionNatural Language InferenceNatural Language UnderstandingQuestion AnsweringReading ComprehensionSemantic Role LabelingWord Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference SNLI SemBERT % Test Accuracy 91.9 #8 of 98 Archive leaderboard report
Natural Language Inference SNLI SemBERT % Train Accuracy 94.4 #8 of 98 Archive leaderboard report
Natural Language Inference SNLI SemBERT Parameters 339m #8 of 98 Archive leaderboard report
Question Answering SQuAD2.0 SemBERT(ensemble) EM 86.166 #106 of 286 Archive leaderboard report
Question Answering SQuAD2.0 SemBERT(ensemble) F1 88.886 #106 of 286 Archive leaderboard report
Question Answering SQuAD2.0 SemBERT (ensemble) EM 86.166 #107 of 286 Archive leaderboard report
Question Answering SQuAD2.0 SemBERT (ensemble) F1 88.886 #107 of 286 Archive leaderboard report
Question Answering SQuAD2.0 SemBERT (single model) EM 84.800 #132 of 286 Archive leaderboard report
Question Answering SQuAD2.0 SemBERT (single model) F1 87.864 #132 of 286 Archive leaderboard report
Question Answering SQuAD2.0 dev SemBERT large EM 80.9 #8 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev SemBERT large F1 83.6 #8 of 13 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

AdamAttentionAttention DropoutBERTBPEBiLSTMCosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutELMoGPTLSTMLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationWeight 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