{"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/word-alignment/papers/6","list_of":"/task/word-alignment","task":"Word Alignment","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":6,"pages_in_order":6,"rows_per_page":100,"rows":[501,551],"of":551,"counts":{"archive_papers_tagged":551,"with_a_code_link":92,"where_syntology_ran_a_sample":23,"not_listed_spam_title":0,"listed":551,"listed_where_code_ran":23,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":20,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":20,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/word-alignment","prev":"/task/word-alignment/papers/5","next":null,"papers":[{"url":null,"slug":"combining-multiple-alignments-to-improve","title":"Combining Multiple Alignments to Improve Machine Translation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-hidden-markov-model-for-bilingual","title":"Constrained Hidden Markov Model for Bilingual Keyword Pairs Alignment","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-identification-of-ambiguous","title":"Cross-Lingual Identification of Ambiguous Discourse Connectives for Resource-Poor Language","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-dependency-parsing-with-interlinear","title":"Improving Dependency Parsing with Interlinear Glossed Text and Syntactic Projection","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"partially-modelling-word-reordering-as-a","title":"Partially modelling word reordering as a sequence labelling problem","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantics-based-machine-translation-with","title":"Semantics-Based Machine Translation with Hyperedge Replacement Grammars","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tibetan-base-noun-phrase-identification","title":"Tibetan Base Noun Phrase Identification Framework Based on Chinese-Tibetan Sentence Aligned Corpus","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-based-translation-without-using-parse","title":"Tree-based Translation without using Parse Trees","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"handling-indonesian-clitics-a-dataset","title":"Handling Indonesian Clitics: A Dataset Comparison for an Indonesian-English Statistical Machine Translation System","date":"2012-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bayesian-model-for-learning-scfgs-with","title":"A Bayesian Model for Learning SCFGs with Discontiguous Rules","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bringing-the-associative-ability-to-social","title":"Bringing the Associative Ability to Social Tag Recommendation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-word-level-and-character-level","title":"Combining Word-Level and Character-Level Models for Machine Translation Between Closely-Related Languages","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domcat-a-bilingual-concordancer-for-domain","title":"DOMCAT: A Bilingual Concordancer for Domain-Specific Computer Assisted Translation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-statistical-machine-translation","title":"Enhancing Statistical Machine Translation with Character Alignment","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"forced-derivation-tree-based-model-training","title":"Forced Derivation Tree based Model Training to Statistical Machine Translation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-sub-sentential-paraphrase","title":"Generalizing Sub-sentential Paraphrase Acquisition across Original Signal Type of Text Pairs","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hdu-cross-lingual-textual-entailment-with-smt","title":"HDU: Cross-lingual Textual Entailment with SMT Features","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-ibm-alignment-models-using","title":"Improving the IBM Alignment Models Using Variational Bayes","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-better-rule-extraction-with","title":"Learning Better Rule Extraction with Translation Span Alignment","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"re-training-monolingual-parser-bilingually","title":"Re-training Monolingual Parser Bilingually for Syntactic SMT","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"smaller-alignment-models-for-better","title":"Smaller Alignment Models for Better Translations: Unsupervised Word Alignment with the l0-norm","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"translation-model-size-reduction-for","title":"Translation Model Size Reduction for Hierarchical Phrase-based Statistical Machine Translation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-parallel-fragment-extraction-from","title":"Automatic Parallel Fragment Extraction from Noisy Data","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"concavity-and-initialization-for-unsupervised","title":"Concavity and Initialization for Unsupervised Dependency Parsing","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"depfix-a-system-for-automatic-correction-of","title":"DEPFIX: A System for Automatic Correction of Czech MT Outputs","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-a-morphological-analyser-of","title":"Evaluating a Morphological Analyser of Inuktitut","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-inference-in-phrase-extraction-models","title":"Fast Inference in Phrase Extraction Models with Belief Propagation","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-alignment-of-narratives-for","title":"Graph-based alignment of narratives for automated neurological assessment","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-comparable-corpora-using-lda","title":"Identifying Comparable Corpora Using LDA","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"insertion-and-deletion-models-for-statistical","title":"Insertion and Deletion Models for Statistical Machine Translation","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"syntax-aware-phrase-based-statistical-machine","title":"Syntax-aware Phrase-based Statistical Machine Translation: System Description","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-karlsruhe-institute-of-technology-2","title":"The Karlsruhe Institute of Technology Translation Systems for the WMT 2012","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-expectation-maximization","title":"Unified Expectation Maximization","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-translation-sense-clustering","title":"Unsupervised Translation Sense Clustering","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-senses-in-hmm-word-alignment","title":"Using Senses in HMM Word Alignment","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"utilisation-de-la-translitteration-arabe-pour","title":"Utilisation de la translitt\\'eration arabe pour l'am\\'elioration de l'alignement de mots \\`a partir de corpus parall\\`eles fran\\ccais-arabe (Using Arabic Transliteration to Improve Word Alignment from French-Arabic Parallel Corpora) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"alignment-based-reordering-for-smt","title":"Alignment-based reordering for SMT","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"annotated-corpora-for-word-alignment-between","title":"Annotated Corpora for Word Alignment between Japanese and English and its Evaluation with MAP-based Word Aligner","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-word-alignment-tools-to-scale","title":"Automatic word alignment tools to scale production of manually aligned parallel texts","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatically-generated-online-dictionaries","title":"Automatically Generated Online Dictionaries","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-word-translations-from-comparable","title":"Identifying Word Translations from Comparable Documents Without a Seed Lexicon","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"word-alignment-for-english-turkish-language","title":"Word Alignment for English-Turkish Language Pair","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatically-generated-customizable-online","title":"Automatically Generated Customizable Online Dictionaries","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-method-for-chunk-alignment-in","title":"Bootstrapping Method for Chunk Alignment in Phrase Based SMT","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-machine-learning-algorithms-improve","title":"Can Machine Learning Algorithms Improve Phrase Selection in Hybrid Machine Translation?","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clustered-word-classes-for-preordering-in","title":"Clustered Word Classes for Preordering in Statistical Machine Translation","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-comparison-through-sparse","title":"Language comparison through sparse multilingual word alignment","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"perplexity-minimization-for-translation-model","title":"Perplexity Minimization for Translation Model Domain Adaptation in Statistical Machine Translation","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"book-review-bitext-alignment-by-jorg","title":"Book Review: Bitext Alignment by J\\\"org Tiedemann","date":"2012-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hm-bitam-bilingual-topic-exploration-word","title":"HM-BiTAM: Bilingual Topic Exploration, Word Alignment, and Translation","date":"2007-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-relationship-between-neural-machine","title":"On the Relationship between Neural Machine Translation and Word Alignment","date":null,"arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"7844b723a50216ff203a5682ef244b9060bde6ef89670f76ad55cccba6b79b19","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}