{"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/deeper-text-understanding-for-ir-with","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","arxiv_id":"1905.09217","date":"2019-05-22","proceeding":null,"authors":["Zhuyun Dai","Jamie Callan"],"abstract":"Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning query-document relevance patterns, but few explorations have been done on understanding the text content of a query or a document. This paper studies leveraging a recently-proposed contextual neural language model, BERT, to provide deeper text understanding for IR. Experimental results demonstrate that the contextual text representations from BERT are more effective than traditional word embeddings. Compared to bag-of-words retrieval models, the contextual language model can better leverage language structures, bringing large improvements on queries written in natural languages. Combining the text understanding ability with search knowledge leads to an enhanced pre-trained BERT model that can benefit related search tasks where training data are limited.","url_abs":"https://arxiv.org/abs/1905.09217v1","url_pdf":"https://arxiv.org/pdf/1905.09217v1.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":"deeper-text-understanding-for-ir-with","repo_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"ad-hoc-information-retrieval","task_name":"Ad-Hoc Information Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"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/ad-hoc-information-retrieval-on-trec-robust04","task":"Ad-Hoc Information Retrieval","dataset":"TREC Robust04","model":"BERT-MaxP","rank_in_archive_order":5,"of":21,"metrics":{"nDCG@20":"0.469"},"uses_additional_data":false},{"leaderboard":"/sota/ad-hoc-information-retrieval-on-trec-robust04","task":"Ad-Hoc Information Retrieval","dataset":"TREC Robust04","model":"BERT-SumP","rank_in_archive_order":6,"of":21,"metrics":{"nDCG@20":"0.467"},"uses_additional_data":false},{"leaderboard":"/sota/ad-hoc-information-retrieval-on-trec-robust04","task":"Ad-Hoc Information Retrieval","dataset":"TREC Robust04","model":"BERT-FirstP","rank_in_archive_order":11,"of":21,"metrics":{"nDCG@20":"0.444"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.09217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09217"}},"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/AdeDZY/SIGIR19-BERT-IR","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":"1923fc05163d207d","entry":"convert_to_unicode","repo":"AdeDZY/SIGIR19-BERT-IR","repo_kind":"official","path":"tokenization.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/tokenization.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"code_sha256_prefix":"5681f7dd9b6e3679","entry":"get_activation","repo":"AdeDZY/SIGIR19-BERT-IR","repo_kind":"official","path":"modeling.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5681f7dd9b6e3679"}},{"code_sha256_prefix":"1b46c9ce24fc6db3","entry":"file_based_input_fn_builder","repo":"AdeDZY/SIGIR19-BERT-IR","repo_kind":"official","path":"run_qe_classifier.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/run_qe_classifier.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1b46c9ce24fc6db3"}},{"code_sha256_prefix":"ecab128238ebf253","entry":"gelu","repo":"AdeDZY/SIGIR19-BERT-IR","repo_kind":"official","path":"modeling.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"code_sha256_prefix":"50958618b65e514e","entry":"get_assignment_map_from_checkpoint","repo":"AdeDZY/SIGIR19-BERT-IR","repo_kind":"official","path":"modeling.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"50958618b65e514e"}},{"code_sha256_prefix":"ff83ccc8b0b6462d","entry":"load_vocab","repo":"AdeDZY/SIGIR19-BERT-IR","repo_kind":"official","path":"tokenization.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/tokenization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"code_sha256_prefix":"0e5615f8994003cf","entry":"printable_text","repo":"AdeDZY/SIGIR19-BERT-IR","repo_kind":"official","path":"tokenization.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/tokenization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0e5615f8994003cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}