{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/structbert-incorporating-language-structures","title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","arxiv_id":"1908.04577","date":"2019-08-13","proceeding":"ICLR 2020 1","authors":["Wei Wang","Bin Bi","Ming Yan","Chen Wu","Zuyi Bao","Jiangnan Xia","Liwei Peng","Luo Si"],"abstract":"Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as sentiment classification, natural language inference, semantic textual similarity and question answering. Inspired by the linearization exploration work of Elman [8], we extend BERT to a new model, StructBERT, by incorporating language structures into pre-training. Specifically, we pre-train StructBERT with two auxiliary tasks to make the most of the sequential order of words and sentences, which leverage language structures at the word and sentence levels, respectively. As a result, the new model is adapted to different levels of language understanding required by downstream tasks. The StructBERT with structural pre-training gives surprisingly good empirical results on a variety of downstream tasks, including pushing the state-of-the-art on the GLUE benchmark to 89.0 (outperforming all published models), the F1 score on SQuAD v1.1 question answering to 93.0, the accuracy on SNLI to 91.7.","url_abs":"https://arxiv.org/abs/1908.04577v3","url_pdf":"https://arxiv.org/pdf/1908.04577v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":13,"of":43,"metrics":{"Accuracy":"69.2%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"Adv-RoBERTa ensemble","rank_in_archive_order":8,"of":67,"metrics":{"Matched":"91.1","Mismatched":"90.7"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-qnli","task":"Natural Language Inference","dataset":"QNLI","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":2,"of":43,"metrics":{"Accuracy":"99.2%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"Adv-RoBERTa ensemble","rank_in_archive_order":17,"of":90,"metrics":{"Accuracy":"88.7%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-wnli","task":"Natural Language Inference","dataset":"WNLI","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":7,"of":23,"metrics":{"Accuracy":"89.7"},"uses_additional_data":false},{"leaderboard":"/sota/paraphrase-identification-on-quora-question","task":"Paraphrase Identification","dataset":"Quora Question Pairs","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":6,"of":31,"metrics":{"Accuracy":"90.7","F1":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/paraphrase-identification-on-wikihop","task":"Paraphrase Identification","dataset":"WikiHop","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"90.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-mrpc","task":"Semantic Textual Similarity","dataset":"MRPC","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":4,"of":45,"metrics":{"Accuracy":"91.5%","F1":"93.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":2,"of":66,"metrics":{"Pearson Correlation":"0.928","Spearman Correlation":"0.924"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"StructBERTRoBERTa ensemble","rank_in_archive_order":6,"of":87,"metrics":{"Accuracy":"97.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.04577","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}