{"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/question-answering-infused-pre-training-of","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","arxiv_id":"2106.08190","date":"2021-06-15","proceeding":"Findings (ACL) 2022 5","authors":["Robin Jia","Mike Lewis","Luke Zettlemoyer"],"abstract":"We propose a pre-training objective based on question answering (QA) for learning general-purpose contextual representations, motivated by the intuition that the representation of a phrase in a passage should encode all questions that the phrase can answer in context. To this end, we train a bi-encoder QA model, which independently encodes passages and questions, to match the predictions of a more accurate cross-encoder model on 80 million synthesized QA pairs. By encoding QA-relevant information, the bi-encoder's token-level representations are useful for non-QA downstream tasks without extensive (or in some cases, any) fine-tuning. We show large improvements over both RoBERTa-large and previous state-of-the-art results on zero-shot and few-shot paraphrase detection on four datasets, few-shot named entity recognition on two datasets, and zero-shot sentiment analysis on three datasets.","url_abs":"https://arxiv.org/abs/2106.08190v2","url_pdf":"https://arxiv.org/pdf/2106.08190v2.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":"question-answering-infused-pre-training-of","repo_url":"https://github.com/facebookresearch/quip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.08190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08190"}},"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/facebookresearch/quip","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"abb1c9dee20a84a2","entry":"find_span","repo":"facebookresearch/quip","repo_kind":"official","path":"src/biencoder_predict_qa.py","file_url":"https://github.com/facebookresearch/quip/blob/HEAD/src/biencoder_predict_qa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"abb1c9dee20a84a2"}},{"code_sha256_prefix":"d47fb782ae3ccffd","entry":"parse_args","repo":"facebookresearch/quip","repo_kind":"official","path":"src/run_sentiment.py","file_url":"https://github.com/facebookresearch/quip/blob/HEAD/src/run_sentiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d47fb782ae3ccffd"}},{"code_sha256_prefix":"7604bdb80f529b88","entry":"read_squad","repo":"facebookresearch/quip","repo_kind":"official","path":"src/biencoder_predict_qa.py","file_url":"https://github.com/facebookresearch/quip/blob/HEAD/src/biencoder_predict_qa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7604bdb80f529b88"}},{"code_sha256_prefix":"b1dd45a0652301b4","entry":"read_data","repo":"facebookresearch/quip","repo_kind":"official","path":"src/run_sentiment.py","file_url":"https://github.com/facebookresearch/quip/blob/HEAD/src/run_sentiment.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b1dd45a0652301b4"}},{"code_sha256_prefix":"d074f1bd08fdac1c","entry":"read_mrqa_all","repo":"facebookresearch/quip","repo_kind":"official","path":"src/biencoder_predict_qa.py","file_url":"https://github.com/facebookresearch/quip/blob/HEAD/src/biencoder_predict_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d074f1bd08fdac1c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}