{"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-similarity/papers/3","list_of":"/task/text-similarity","task":"text similarity","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":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,271],"of":271,"counts":{"archive_papers_tagged":271,"with_a_code_link":100,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":271,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":15,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":15,"listed_every_run_a_failure_of_syntologys_instrument":0,"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-similarity","prev":"/task/text-similarity/papers/2","next":null,"papers":[{"url":null,"slug":"lesslex-linking-multilingual-embeddings-to","title":"LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sentpwnet-a-unified-sentence-pair-weighting","title":"SentPWNet: A Unified Sentence Pair Weighting Network for Task-specific Sentence Embedding","date":"2020-05-22","arxiv_id":"2005.11347","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommendation-chart-of-domains-for-cross-1","title":"Recommendation Chart of Domains for Cross-Domain Sentiment Analysis: Findings of A 20 Domain Study","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-better-universal-representations","title":"BURT: BERT-inspired Universal Representation from Twin Structure","date":"2020-04-29","arxiv_id":"2004.13947","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-word-embeddings-and-n-grams-for","title":"Combining Word Embeddings and N-grams for Unsupervised Document Summarization","date":"2020-04-25","arxiv_id":"2004.14119","repositories_listed":0,"syntology":null},{"url":"/paper/textual-visual-semantic-dataset-for-text","slug":"textual-visual-semantic-dataset-for-text","title":"Textual Visual Semantic Dataset for Text Spotting","date":"2020-04-21","arxiv_id":"2004.10349","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommendation-chart-of-domains-for-cross","title":"Recommendation Chart of Domains for Cross-Domain Sentiment Analysis:Findings of A 20 Domain Study","date":"2020-04-09","arxiv_id":"2004.04478","repositories_listed":0,"syntology":null},{"url":null,"slug":"locality-preserving-loss-to-align-vector","title":"Locality Preserving Loss: Neighbors that Live together, Align together","date":"2020-04-07","arxiv_id":"2004.03734","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-classification-model-for-igbo","title":"Comparative Analysis of N-gram Text Representation on Igbo Text Document Similarity","date":"2020-04-01","arxiv_id":"2004.00375","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-similarity-using-word-embeddings-to","title":"Text Similarity Using Word Embeddings to Classify Misinformation","date":"2020-03-14","arxiv_id":"2003.06634","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multimodal-image-text-embeddings-for","title":"Deep Multimodal Image-Text Embeddings for Automatic Cross-Media Retrieval","date":"2020-02-23","arxiv_id":"2002.10016","repositories_listed":0,"syntology":null},{"url":null,"slug":"expressing-objects-just-like-words-recurrent","title":"Expressing Objects just like Words: Recurrent Visual Embedding for Image-Text Matching","date":"2020-02-20","arxiv_id":"2002.08510","repositories_listed":0,"syntology":null},{"url":null,"slug":"testing-of-support-tools-for-plagiarism","title":"Testing of Support Tools for Plagiarism Detection","date":"2020-02-11","arxiv_id":"2002.04279","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-quantifying-the-distance-between","title":"Towards Quantifying the Distance between Opinions","date":"2020-01-27","arxiv_id":"2001.09879","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-similarity-learning-with-feedback-for","title":"Online Similarity Learning with Feedback for Invoice Line Item Matching","date":"2020-01-02","arxiv_id":"2001.00288","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-relevance-matching","title":"Bridging the Gap between Relevance Matching and Semantic Matching for Short Text Similarity Modeling","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-heuristically-modified-fp-tree-for-ontology","title":"A Heuristically Modified FP-Tree for Ontology Learning with Applications in Education","date":"2019-10-29","arxiv_id":"1910.13561","repositories_listed":0,"syntology":null},{"url":null,"slug":"ordinal-and-attribute-aware-response","title":"Ordinal and Attribute Aware Response Generation in a Multimodal Dialogue System","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parnet-position-aware-aggregated-relation","title":"ParNet: Position-aware Aggregated Relation Network for Image-Text matching","date":"2019-06-17","arxiv_id":"1906.06892","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-similarity-estimation-based-on-word","title":"Text Similarity Estimation Based on Word Embeddings and Matrix Norms for Targeted Marketing","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-knowledge-graph-based-solution-for-entity","title":"A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions","date":"2018-12-05","arxiv_id":"1812.01889","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-embedding-based-edit-distance","title":"Word Embedding based Edit Distance","date":"2018-10-25","arxiv_id":"1810.10752","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fast-text-similarity-measure-for-large","title":"A Fast Text Similarity Measure for Large Document Collections using Multi-reference Cosine and Genetic Algorithm","date":"2018-10-07","arxiv_id":"1810.03102","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-evaluation-of-multimodal-machine","title":"Adversarial Evaluation of Multimodal Machine Translation","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-similarity-in-vector-space-models-a","title":"Text Similarity in Vector Space Models: A Comparative Study","date":"2018-09-24","arxiv_id":"1810.00664","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-method-for-human-interpretable","title":"A Method for Human-Interpretable Paraphrasticality Prediction","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"peperomia-at-semeval-2018-task-2-vector","title":"Peperomia at SemEval-2018 Task 2: Vector Similarity Based Approach for Emoji Prediction","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-network-transfer-transfer-learning-of","title":"Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity","date":"2018-04-20","arxiv_id":"1804.07835","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-low-dimensional-vector","title":"Unsupervised Low-Dimensional Vector Representations for Words, Phrases and Text that are Transparent, Scalable, and produce Similarity Metrics that are Complementary to Neural Embeddings","date":"2018-01-05","arxiv_id":"1801.01884","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimation-of-cross-lingual-news-similarities","title":"Estimation of cross-lingual news similarities using text-mining methods","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-based-text-similarity-measure-that","title":"A Graph-based Text Similarity Measure That Employs Named Entity Information","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-approach-to-recognizing-cst","title":"Graph-Based Approach to Recognizing CST Relations in Polish Texts","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beihang-msra-at-semeval-2017-task-3-a-ranking","title":"Beihang-MSRA at SemEval-2017 Task 3: A Ranking System with Neural Matching Features for Community Question Answering","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-contextual-embeddings-for-structural","title":"Learning Contextual Embeddings for Structural Semantic Similarity using Categorical Information","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"textflow-a-text-similarity-measure-based-on","title":"TextFlow: A Text Similarity Measure based on Continuous Sequences","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"content-based-similar-document-image","title":"Content-based similar document image retrieval using fusion of CNN features","date":"2017-03-23","arxiv_id":"1703.08013","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-german-corpus-for-text-similarity-detection","title":"A German Corpus for Text Similarity Detection Tasks","date":"2017-03-11","arxiv_id":"1703.03923","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-vector-representations-for","title":"Distributed Vector Representations for Unsupervised Automatic Short Answer Grading","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"get-semantic-with-me-the-usefulness-of","title":"Get Semantic With Me! The Usefulness of Different Feature Types for Short-Answer Grading","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-extractive-sentence-intersection-via","title":"Modeling Extractive Sentence Intersection via Subtree Entailment","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-rank-scientific-documents-from","title":"Learning to Rank Scientific Documents from the Crowd","date":"2016-11-04","arxiv_id":"1611.01400","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-focused-opinion-summarization-for-user","title":"Query-Focused Opinion Summarization for User-Generated Content","date":"2016-06-17","arxiv_id":"1606.05702","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-supervised-domain-adaptation-for","title":"Bayesian Supervised Domain Adaptation for Short Text Similarity","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dalgtm-at-semeval-2016-task-1-importance","title":"DalGTM at SemEval-2016 Task 1: Importance-Aware Compositional Approach to Short Text Similarity","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"normas-at-semeval-2016-task-1-semsim-a-multi","title":"NORMAS at SemEval-2016 Task 1: SEMSIM: A Multi-Feature Approach to Semantic Text Similarity","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uob-uk-at-semeval-2016-task-1-a-flexible-and","title":"UoB-UK at SemEval-2016 Task 1: A Flexible and Extendable System for Semantic Text Similarity using Types, Surprise and Phrase Linking","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semaligner-a-method-and-tool-for-aligning","title":"SemAligner: A Method and Tool for Aligning Chunks with Semantic Relation Types and Semantic Similarity Scores","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-semantic-similarity-for-very-short","title":"Learning Semantic Similarity for Very Short Texts","date":"2015-12-02","arxiv_id":"1512.00765","repositories_listed":0,"syntology":null},{"url":null,"slug":"computing-semantic-text-similarity-using-rich","title":"Computing Semantic Text Similarity Using Rich Features","date":"2015-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"yigou-a-semantic-text-similarity-computing","title":"yiGou: A Semantic Text Similarity Computing System Based on SVM","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-feature-integration-for-automated","title":"Effective Feature Integration for Automated Short Answer Scoring","date":"2015-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-sparse-vector-densification-for","title":"Unsupervised Sparse Vector Densification for Short Text Similarity","date":"2015-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-tomaco-hybrid-matching-framework-for","title":"The Tomaco Hybrid Matching Framework for SAWSDL Semantic Web Services","date":"2014-10-21","arxiv_id":"1410.5614","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-use-of-text-similarity-and-sentiment","title":"The Use of Text Similarity and Sentiment Analysis to Examine Rationales in the Large-Scale Online Deliberations","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"missed-opportunities-in-translation-memory","title":"Missed opportunities in translation memory matching","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dkpro-similarity-an-open-source-framework-for","title":"DKPro Similarity: An Open Source Framework for Text Similarity","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ecnucs-recognizing-cross-lingual-textual","title":"ECNUCS: Recognizing Cross-lingual Textual Entailment Using Multiple Text Similarity and Text Difference Measures","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"henry-core-domain-adaptation-and-stacking-for","title":"HENRY-CORE: Domain Adaptation and Stacking for Text Similarity","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knce2013-coresemantic-text-similarity-by-use","title":"KnCe2013-CORE:Semantic Text Similarity by use of Knowledge Bases","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lipn-core-semantic-text-similarity-using-n","title":"LIPN-CORE: Semantic Text Similarity using n-grams, WordNet, Syntactic Analysis, ESA and Information Retrieval based Features","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unitor-core_typed-combining-text-similarity","title":"UNITOR-CORE\\_TYPED: Combining Text Similarity and Semantic Filters through SV Regression","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-academic-research-paper","title":"Personalized Academic Research Paper Recommendation System","date":"2013-04-19","arxiv_id":"1304.5457","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-reuse-detection-using-a-composition-of","title":"Text Reuse Detection using a Composition of Text Similarity Measures","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ata-sem-chunk-based-determination-of-semantic","title":"ATA-Sem: Chunk-based Determination of Semantic Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"takelab-systems-for-measuring-semantic-text","title":"TakeLab: Systems for Measuring Semantic Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uned-improving-text-similarity-measures","title":"UNED: Improving Text Similarity Measures without Human Assessments","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unitor-combining-semantic-text-similarity","title":"UNITOR: Combining Semantic Text Similarity functions through SV Regression","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"university_of_sheffield-two-approaches-to","title":"University\\_Of\\_Sheffield: Two Approaches to Semantic Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unt-a-supervised-synergistic-approach-to","title":"UNT: A Supervised Synergistic Approach to Semantic Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uow-semantically-informed-text-similarity","title":"UOW: Semantically Informed Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dss-text-similarity-using-lexical-alignments","title":"DSS: Text Similarity Using Lexical Alignments of Form, Distributional Semantics and Grammatical Relations","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"60e755f332b740db1d016006b4d6c93a3706e3307d28ee54aed2c8c6fb60d330","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}