{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-retrieval/papers/7","list_of":"/task/text-retrieval","task":"Text Retrieval","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":7,"rows_per_page":100,"rows":[601,671],"of":671,"counts":{"archive_papers_tagged":671,"with_a_code_link":335,"where_syntology_ran_a_sample":117,"not_listed_spam_title":0,"listed":671,"listed_where_code_ran":117,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":18,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/text-retrieval","prev":"/task/text-retrieval/papers/6","next":null,"papers":[{"url":null,"slug":"text-retrieval-for-language-learners-graded","title":"Text Retrieval for Language Learners: Graded Vocabulary vs. Open Learner Model","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"in-batch-negatives-for-knowledge-distillation","title":"In-Batch Negatives for Knowledge Distillation with Tightly-Coupled Teachers for Dense Retrieval","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-or-text-retrieval-or-bert","title":"Multimodal or Text? Retrieval or BERT? Benchmarking Classifiers for the Shared Task on Hateful Memes","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-inter-modality-visual-parsing-with","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","date":"2021-06-25","arxiv_id":"2106.13488","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-cross-modal-prototypes-for-cross","title":"Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Language Retrieval","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-bert-dig-it-named-entity-recognition-for","title":"Can BERT Dig It? -- Named Entity Recognition for Information Retrieval in the Archaeology Domain","date":"2021-06-14","arxiv_id":"2106.07742","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-we-there-yet-exploring-clinical-domain","title":"Are we there yet? Exploring clinical domain knowledge of BERT models","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-visual-semantic-embedding-methods","title":"Survey of Visual-Semantic Embedding Methods for Zero-Shot Image Retrieval","date":"2021-05-16","arxiv_id":"2105.07391","repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-lottery-tickets-with-vision-and","title":"Playing Lottery Tickets with Vision and Language","date":"2021-04-23","arxiv_id":"2104.11832","repositories_listed":0,"syntology":null},{"url":null,"slug":"uhd-bert-bucketed-ultra-high-dimensional","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","date":"2021-04-15","arxiv_id":"2104.07198","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-in-cross-modal-retrieval","title":"Continual learning in cross-modal retrieval","date":"2021-04-14","arxiv_id":"2104.06806","repositories_listed":0,"syntology":null},{"url":null,"slug":"spotify-at-trec-2020-genre-aware-abstractive","title":"Spotify at TREC 2020: Genre-Aware Abstractive Podcast Summarization","date":"2021-04-07","arxiv_id":"2104.03343","repositories_listed":0,"syntology":null},{"url":null,"slug":"uc2-universal-cross-lingual-cross-modal","title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training","date":"2021-04-01","arxiv_id":"2104.00332","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-enhanced-embedding-learning-for-cross","title":"Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval","date":"2021-03-29","arxiv_id":"2103.15686","repositories_listed":0,"syntology":null},{"url":null,"slug":"trec-2020-podcasts-track-overview","title":"TREC 2020 Podcasts Track Overview","date":"2021-03-29","arxiv_id":"2103.15953","repositories_listed":0,"syntology":null},{"url":null,"slug":"hit-hierarchical-transformer-with-momentum","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","date":"2021-03-28","arxiv_id":"2103.15049","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effects-of-having-lists-of-synonyms-on","title":"The effects of having lists of synonyms on the performance of Afaan Oromo Text Retrieval system","date":"2021-03-04","arxiv_id":"2103.02900","repositories_listed":0,"syntology":null},{"url":null,"slug":"doc2ppt-automatic-presentation-slides","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","date":"2021-01-28","arxiv_id":"2101.11796","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attack-on-deep-cross-modal","title":"Adversarial Attack on Deep Cross-Modal Hamming Retrieval","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-document-expansion-for-ad-hoc","title":"Neural document expansion for ad-hoc information retrieval","date":"2020-12-27","arxiv_id":"2012.14005","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-predicting-the-1","title":"Understanding and Predicting Characteristics of Test Collections in Information Retrieval","date":"2020-12-24","arxiv_id":"2012.13292","repositories_listed":0,"syntology":null},{"url":null,"slug":"denmark-s-participation-in-the-search-engine","title":"Denmark's Participation in the Search Engine TREC COVID-19 Challenge: Lessons Learned about Searching for Precise Biomedical Scientific Information on COVID-19","date":"2020-11-25","arxiv_id":"2011.12684","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchical-gumbel-attention-network-for","slug":"hierarchical-gumbel-attention-network-for","title":"Hierarchical Gumbel Attention Network for Text-based Person Search","date":"2020-10-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sparterm-learning-term-based-sparse","title":"SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval","date":"2020-10-02","arxiv_id":"2010.00768","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-visione-video-search-system-exploiting","title":"The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval","date":"2020-08-06","arxiv_id":"2008.02749","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-joint-visual-semantic-matching","title":"Learning Joint Visual Semantic Matching Embeddings for Language-guided Retrieval","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-visual-semantic-reasoning-for","title":"Exploiting Visual Semantic Reasoning for Video-Text Retrieval","date":"2020-06-16","arxiv_id":"2006.08889","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-reinforcement-learning-training","title":"Balancing Reinforcement Learning Training Experiences in Interactive Information Retrieval","date":"2020-06-05","arxiv_id":"2006.03185","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-makes-a-top-performing-precision","title":"What Makes a Top-Performing Precision Medicine Search Engine? Tracing Main System Features in a Systematic Way","date":"2020-06-04","arxiv_id":"2006.02785","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-modal-nonlinear-embeddings","title":"Learning Multi-Modal Nonlinear Embeddings: Performance Bounds and an Algorithm","date":"2020-06-03","arxiv_id":"2006.02330","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-attention-network-for-image","title":"Context-Aware Attention Network for Image-Text Retrieval","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-language-models-for-similar","title":"Transformer Based Language Models for Similar Text Retrieval and Ranking","date":"2020-05-10","arxiv_id":"2005.04588","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-investigative-study-of-multi-modal-cross","title":"An Investigative Study of Multi-Modal Cross-Lingual Retrieval","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-deep-gaussian-processes-for","title":"Evaluation of Deep Gaussian Processes for Text Classification","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stacked-convolutional-deep-encoding-network","title":"Stacked Convolutional Deep Encoding Network for Video-Text Retrieval","date":"2020-04-10","arxiv_id":"2004.04959","repositories_listed":0,"syntology":null},{"url":"/paper/xgpt-cross-modal-generative-pre-training-for","slug":"xgpt-cross-modal-generative-pre-training-for","title":"XGPT: Cross-modal Generative Pre-Training for Image Captioning","date":"2020-03-03","arxiv_id":"2003.01473","repositories_listed":0,"syntology":null},{"url":null,"slug":"experiments-with-different-indexing","title":"Experiments with Different Indexing Techniques for Text Retrieval tasks on Gujarati Language using Bag of Words Approach","date":"2020-02-05","arxiv_id":"2002.01792","repositories_listed":0,"syntology":null},{"url":"/paper/imagebert-cross-modal-pre-training-with-large","slug":"imagebert-cross-modal-pre-training-with-large","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","date":"2020-01-22","arxiv_id":"2001.07966","repositories_listed":0,"syntology":null},{"url":null,"slug":"show-recall-and-tell-image-captioning-with","title":"Show, Recall, and Tell: Image Captioning with Recall Mechanism","date":"2020-01-15","arxiv_id":"2001.05876","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-learning-for-text-retrieval-and","title":"Lifelong learning for text retrieval and recognition in historical handwritten document collections","date":"2019-12-11","arxiv_id":"1912.05156","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-embedding-using-hierarchical-structure","title":"Label Embedding using Hierarchical Structure of Labels for Twitter Classification","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uniter-learning-universal-image-text","title":"UNITER: Learning UNiversal Image-TExt Representations","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/unicoder-vl-a-universal-encoder-for-vision","slug":"unicoder-vl-a-universal-encoder-for-vision","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","date":"2019-08-16","arxiv_id":"1908.06066","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-minimax-game-for-instance-based-selective","title":"A Minimax Game for Instance based Selective Transfer Learning","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transformation-of-xml-documents-with-prolog","title":"Transformation of XML Documents with Prolog","date":"2019-06-19","arxiv_id":"1906.08361","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-medical-literature-search-system-for","title":"A Medical Literature Search System for Identifying Effective Treatments in Precision Medicine","date":"2019-04-16","arxiv_id":"1904.07428","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-semantic-multimodal-hashing-network-for","title":"Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals","date":"2019-01-09","arxiv_id":"1901.02662","repositories_listed":0,"syntology":null},{"url":null,"slug":"c-dlsi-an-extended-lsi-tailored-for-federated","title":"C-DLSI: An Extended LSI Tailored for Federated Text Retrieval","date":"2018-10-05","arxiv_id":"1810.02579","repositories_listed":0,"syntology":null},{"url":null,"slug":"webly-supervised-joint-embedding-for-cross-1","title":"Webly Supervised Joint Embedding for Cross-Modal lmage-Text Retrieval","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mias-math-aware-retrieval-in-digital","title":"MIaS: Math-Aware Retrieval in Digital Mathematical Libraries","date":"2018-08-28","arxiv_id":"1808.09224","repositories_listed":0,"syntology":null},{"url":null,"slug":"webly-supervised-joint-embedding-for-cross","title":"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval","date":"2018-08-23","arxiv_id":"1808.07793","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-text-retrieval-for-learners-of","title":"Personalized Text Retrieval for Learners of Chinese as a Foreign Language","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-combinations-of-ontological","title":"Exploring Combinations of Ontological Features and Keywords for Text Retrieval","date":"2018-07-20","arxiv_id":"1807.07966","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-equilibrium-of-query-reformulation-and","title":"On the Equilibrium of Query Reformulation and Document Retrieval","date":"2018-07-20","arxiv_id":"1807.02299","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-search-by-latent-ontological","title":"Semantic Search by Latent Ontological Features","date":"2018-07-15","arxiv_id":"1807.05576","repositories_listed":0,"syntology":null},{"url":null,"slug":"mesh-based-dataset-for-measuring-the","title":"MeSH-based dataset for measuring the relevance of text retrieval","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"look-imagine-and-match-improving-textual","title":"Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models","date":"2017-11-17","arxiv_id":"1711.06420","repositories_listed":0,"syntology":null},{"url":null,"slug":"hashtag-processing-for-enhanced-clustering-of","title":"Hashtag Processing for Enhanced Clustering of Tweets","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"word-searching-in-scene-image-and-video-frame","title":"Word Searching in Scene Image and Video Frame in Multi-Script Scenario using Dynamic Shape Coding","date":"2017-08-18","arxiv_id":"1708.05529","repositories_listed":0,"syntology":null},{"url":"/paper/biosses-a-semantic-sentence-similarity","slug":"biosses-a-semantic-sentence-similarity","title":"BIOSSES: A Semantic Sentence Similarity Estimation System for the Biomedical Domain","date":"2017-07-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unambiguous-text-localization-and-retrieval","title":"Unambiguous Text Localization and Retrieval for Cluttered Scenes","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-indexing-of-multilingual-corpora-and","title":"Semantic Indexing of Multilingual Corpora and its Application on the History Domain","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-retrieval-by-term-co-occurrences-in-a","title":"Text Retrieval by Term Co-occurrences in a Query-based Vector Space","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"searching-four-millenia-old-digitized","title":"Searching Four-Millenia-Old Digitized Documents: A Text Retrieval System for Egyptologists","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-reducing-the-number-of-visual-words-in-the","title":"On Reducing the Number of Visual Words in the Bag-of-Features Representation","date":"2016-04-14","arxiv_id":"1604.04142","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetrically-weighted-cca-and-hierarchical","title":"Asymmetrically Weighted CCA And Hierarchical Kernel Sentence Embedding For Image & Text Retrieval","date":"2015-11-19","arxiv_id":"1511.06267","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-statistical-consistency-of-plug-in","title":"On the Statistical Consistency of Plug-in Classifiers for Non-decomposable Performance Measures","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nomad-linguistic-resources-and-tools-aimed-at","title":"NOMAD: Linguistic Resources and Tools Aimed at Policy Formulation and Validation","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-relatedness-based-on-a-word-thesaurus","title":"Text Relatedness Based on a Word Thesaurus","date":"2014-01-15","arxiv_id":"1401.5699","repositories_listed":0,"syntology":null},{"url":null,"slug":"abc-sg-a-new-artificial-bee-colony-algorithm","title":"ABC-SG: A New Artificial Bee Colony Algorithm-Based Distance of Sequential Data Using Sigma Grams","date":"2013-12-05","arxiv_id":"1312.1423","repositories_listed":0,"syntology":null},{"url":null,"slug":"angular-quantization-based-binary-codes-for","title":"Angular Quantization-based Binary Codes for Fast Similarity Search","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"a270af4354bd00e6406c2a5a3521339c2c624f854a42c98ebc741ebf016a313f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}