{"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/augmented-sbert-data-augmentation-method-for","title":"Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks","arxiv_id":"2010.08240","date":"2020-10-16","proceeding":"NAACL 2021 4","authors":["Nandan Thakur","Nils Reimers","Johannes Daxenberger","Iryna Gurevych"],"abstract":"There are two approaches for pairwise sentence scoring: Cross-encoders, which perform full-attention over the input pair, and Bi-encoders, which map each input independently to a dense vector space. While cross-encoders often achieve higher performance, they are too slow for many practical use cases. Bi-encoders, on the other hand, require substantial training data and fine-tuning over the target task to achieve competitive performance. We present a simple yet efficient data augmentation strategy called Augmented SBERT, where we use the cross-encoder to label a larger set of input pairs to augment the training data for the bi-encoder. We show that, in this process, selecting the sentence pairs is non-trivial and crucial for the success of the method. We evaluate our approach on multiple tasks (in-domain) as well as on a domain adaptation task. Augmented SBERT achieves an improvement of up to 6 points for in-domain and of up to 37 points for domain adaptation tasks compared to the original bi-encoder performance.","url_abs":"https://arxiv.org/abs/2010.08240v2","url_pdf":"https://arxiv.org/pdf/2010.08240v2.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":[{"paper_slug":"augmented-sbert-data-augmentation-method-for","repo_url":"https://github.com/UKPLab/sentence-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"paraphrase-identification-within-bi-encoder","task_name":"Paraphrase Identification within Bi-Encoder"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"semantic-textual-similarity-within-bi-encoder","task_name":"Semantic Textual Similarity within Bi-Encoder"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-pair-modeling","task_name":"Sentence Pair Modeling"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"augmented-sbert","method_name":"Augmented SBERT"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"sbert","method_name":"SBERT"},{"method_slug":"siamese-network","method_name":"Siamese Network"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"augmented-sbert","name":"Augmented SBERT","full_name":"Augmented SBERT"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.08240","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}