{"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/span-selection-pre-training-for-question","title":"Span Selection Pre-training for Question Answering","arxiv_id":"1909.04120","date":"2019-09-09","proceeding":"ACL 2020 6","authors":["Michael Glass","Alfio Gliozzo","Rishav Chakravarti","Anthony Ferritto","Lin Pan","G P Shrivatsa Bhargav","Dinesh Garg","Avirup Sil"],"abstract":"BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). BERT is pre-trained on two auxiliary tasks: Masked Language Model and Next Sentence Prediction. In this paper we introduce a new pre-training task inspired by reading comprehension to better align the pre-training from memorization to understanding. Span Selection Pre-Training (SSPT) poses cloze-like training instances, but rather than draw the answer from the model's parameters, it is selected from a relevant passage. We find significant and consistent improvements over both BERT-BASE and BERT-LARGE on multiple reading comprehension (MRC) datasets. Specifically, our proposed model has strong empirical evidence as it obtains SOTA results on Natural Questions, a new benchmark MRC dataset, outperforming BERT-LARGE by 3 F1 points on short answer prediction. We also show significant impact in HotpotQA, improving answer prediction F1 by 4 points and supporting fact prediction F1 by 1 point and outperforming the previous best system. Moreover, we show that our pre-training approach is particularly effective when training data is limited, improving the learning curve by a large amount.","url_abs":"https://arxiv.org/abs/1909.04120v2","url_pdf":"https://arxiv.org/pdf/1909.04120v2.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":"span-selection-pre-training-for-question","repo_url":"https://github.com/IBM/span-selection-pretraining","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"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":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.04120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04120"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/span-selection-pretraining","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d6b89c7b58978a8d","entry":"expand_files","repo":"IBM/span-selection-pretraining","repo_kind":"official","path":"util/line_corpus.py","file_url":"https://github.com/IBM/span-selection-pretraining/blob/HEAD/util/line_corpus.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6b89c7b58978a8d"}},{"code_sha256_prefix":"0f9f2dcb10508687","entry":"find_answer_starts","repo":"IBM/span-selection-pretraining","repo_kind":"official","path":"sspt/rc_data.py","file_url":"https://github.com/IBM/span-selection-pretraining/blob/HEAD/sspt/rc_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f9f2dcb10508687"}},{"code_sha256_prefix":"85c7c7b7f3166299","entry":"jsonl_files","repo":"IBM/span-selection-pretraining","repo_kind":"official","path":"util/line_corpus.py","file_url":"https://github.com/IBM/span-selection-pretraining/blob/HEAD/util/line_corpus.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"85c7c7b7f3166299"}},{"code_sha256_prefix":"652308c8c6436531","entry":"jsonl_lines","repo":"IBM/span-selection-pretraining","repo_kind":"official","path":"util/line_corpus.py","file_url":"https://github.com/IBM/span-selection-pretraining/blob/HEAD/util/line_corpus.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"652308c8c6436531"}},{"code_sha256_prefix":"d8293148b27d48c6","entry":"make_batch","repo":"IBM/span-selection-pretraining","repo_kind":"official","path":"sspt/rc_data.py","file_url":"https://github.com/IBM/span-selection-pretraining/blob/HEAD/sspt/rc_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8293148b27d48c6"}},{"code_sha256_prefix":"05976f47d8d6e84a","entry":"normalize","repo":"IBM/span-selection-pretraining","repo_kind":"official","path":"sspt/rc_data.py","file_url":"https://github.com/IBM/span-selection-pretraining/blob/HEAD/sspt/rc_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05976f47d8d6e84a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}