{"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/complex-word-identification","name":"Complex Word Identification","slug":"complex-word-identification","description_markdown":"Identifying difficult words or expressions in a text.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":67,"papers_with_code":8,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/mwe-cwi","name":"MWE-CWI","full_name":null,"num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":67,"of":67,"of_with_code":8,"tagged_in_all":67,"counts":{"archive_papers_tagged":67,"with_a_code_link":8,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":67,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"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"},"items":[{"url":"/paper/cs60075-team2-at-semeval-2021-task-1-lexical","slug":"cs60075-team2-at-semeval-2021-task-1-lexical","title":"cs60075_team2 at SemEval-2021 Task 1 : Lexical Complexity Prediction using Transformer-based Language Models pre-trained on various text corpora","date":"2021-06-04","arxiv_id":"2106.02340","repositories_listed":2,"syntology":null},{"url":"/paper/investigating-large-language-models-for-1","slug":"investigating-large-language-models-for-1","title":"Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups","date":"2024-11-03","arxiv_id":"2411.01706","repositories_listed":1,"syntology":null},{"url":"/paper/difficult-for-whom-a-study-of-japanese","slug":"difficult-for-whom-a-study-of-japanese","title":"Difficult for Whom? A Study of Japanese Lexical Complexity","date":"2024-10-24","arxiv_id":"2410.18567","repositories_listed":1,"syntology":null},{"url":"/paper/a-user-centered-evaluation-of-spanish-text","slug":"a-user-centered-evaluation-of-spanish-text","title":"A User-Centered Evaluation of Spanish Text Simplification","date":"2023-08-15","arxiv_id":"2308.07556","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-multiword-expression-type-helps","slug":"detecting-multiword-expression-type-helps","title":"Detecting Multiword Expression Type Helps Lexical Complexity Assessment","date":"2020-05-12","arxiv_id":"2005.05692","repositories_listed":1,"syntology":null},{"url":"/paper/complex-a-new-corpus-for-lexical-complexity","slug":"complex-a-new-corpus-for-lexical-complexity","title":"CompLex: A New Corpus for Lexical Complexity Prediction from Likert Scale Data","date":"2020-03-16","arxiv_id":"2003.07008","repositories_listed":1,"syntology":null},{"url":"/paper/complex-word-identification-as-a-sequence","slug":"complex-word-identification-as-a-sequence","title":"Complex Word Identification as a Sequence Labelling Task","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/strong-baselines-for-complex-word","slug":"strong-baselines-for-complex-word","title":"Strong Baselines for Complex Word Identification across Multiple Languages","date":"2019-04-11","arxiv_id":"1904.05953","repositories_listed":1,"syntology":null},{"url":null,"slug":"new-evaluation-paradigm-for-lexical","title":"New Evaluation Paradigm for Lexical Simplification","date":"2025-01-25","arxiv_id":"2501.15268","repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-word-identification-in-vietnamese","title":"Complex Word Identification in Vietnamese: Towards Vietnamese Text Simplification","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cwid-hi-a-dataset-for-complex-word","title":"CWID-hi: A Dataset for Complex Word Identification in Hindi Text","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-in-multilingual-and-multi-1","title":"Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word Identification","date":"2022-05-15","arxiv_id":"2205.07283","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-size-does-not-fit-all-the-case-for","title":"One Size Does Not Fit All: The Case for Personalised Word Complexity Models","date":"2022-05-05","arxiv_id":"2205.02564","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-using-gaze-behaviour-for-natural","title":"A Survey on Using Gaze Behaviour for Natural Language Processing","date":"2021-12-21","arxiv_id":"2112.15471","repositories_listed":0,"syntology":null},{"url":null,"slug":"clexis2-a-new-corpus-for-complex-word","title":"CLexIS2: A New Corpus for Complex Word Identification Research in Computing Studies","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iapucp-at-semeval-2021-task-1-stacking-fine","title":"IAPUCP at SemEval-2021 Task 1: Stacking Fine-Tuned Transformers is Almost All You Need for Lexical Complexity Prediction","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"manchester-metropolitan-at-semeval-2021-task","title":"Manchester Metropolitan at SemEval-2021 Task 1: Convolutional Networks for Complex Word Identification","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-lexical-complexity-in-english","title":"Predicting Lexical Complexity in English Texts: The Complex 2.0 Dataset","date":"2021-02-17","arxiv_id":"2102.08773","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-learning-for-complex","title":"Cross-Lingual Transfer Learning for Complex Word Identification","date":"2020-10-02","arxiv_id":"2010.01108","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-neural-cwi-classifiers-weights","title":"Interpreting Neural CWI Classifiers' Weights as Vocabulary Size","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-a-new-corpus-for-lexical-complexity-1","title":"CompLex --- A New Corpus for Lexical Complexity Prediction from Likert Scale Data","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"secoda-sense-complexity-dataset","title":"SeCoDa: Sense Complexity Dataset","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-complex-word-identification","title":"Multilingual Complex Word Identification: Convolutional Neural Networks with Morphological and Linguistic Features","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-judgments-are-more-consistent","title":"Comparative judgments are more consistent than binary classification for labelling word complexity","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-interface-between-readability-and","title":"The Interface Between Readability and Automatic Text Simplification","date":"2018-11-01","arxiv_id":null,"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":"personalizing-lexical-simplification","title":"Personalizing Lexical Simplification","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"camb-at-cwi-shared-task-2018-complex-word","title":"CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-word-identification-based-on","title":"Complex Word Identification Based on Frequency in a Learner Corpus","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-word-identification-convolutional","title":"Complex Word Identification: Convolutional Neural Network vs. Feature Engineering","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-word-identification-using-character-n","title":"Complex Word Identification Using Character n-grams","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-complex-word-identification","title":"Cross-lingual complex word identification with multitask learning","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-architecture-for-complex-word","title":"Deep Learning Architecture for Complex Word Identification","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lastustaln-at-complex-word-identification-cwi","title":"LaSTUS/TALN at Complex Word Identification (CWI) 2018 Shared Task","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nilc-at-cwi-2018-exploring-feature","title":"NILC at CWI 2018: Exploring Feature Engineering and Feature Learning","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nt2lex-a-cefr-graded-lexical-resource-for","title":"NT2Lex: A CEFR-Graded Lexical Resource for Dutch as a Foreign Language Linked to Open Dutch WordNet","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sbgu-at-the-complex-word-identification-2018","title":"SB@GU at the Complex Word Identification 2018 Shared Task","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simplification-using-paraphrases-and-context","title":"Simplification Using Paraphrases and Context-Based Lexical Substitution","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-whole-is-greater-than-the-sum-of-its","title":"The Whole is Greater than the Sum of its Parts: Towards the Effectiveness of Voting Ensemble Classifiers for Complex Word Identification","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-report-on-the-complex-word-identification","title":"A Report on the Complex Word Identification Shared Task 2018","date":"2018-04-24","arxiv_id":"1804.09132","repositories_listed":0,"syntology":null},{"url":null,"slug":"unibuckernel-a-kernel-based-learning-method","title":"UnibucKernel: A kernel-based learning method for complex word identification","date":"2018-03-20","arxiv_id":"1803.07602","repositories_listed":0,"syntology":null},{"url":null,"slug":"cwig3g2-complex-word-identification-task","title":"CWIG3G2 - Complex Word Identification Task across Three Text Genres and Two User Groups","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-word-identification-challenges-in","title":"Complex Word Identification: Challenges in Data Annotation and System Performance","date":"2017-10-13","arxiv_id":"1710.04989","repositories_listed":0,"syntology":null},{"url":null,"slug":"clac-at-semeval-2016-task-11-exploring","title":"CLaC at SemEval-2016 Task 11: Exploring linguistic and psycho-linguistic Features for Complex Word Identification","date":"2017-09-08","arxiv_id":"1709.02843","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-and-cross-lingual-complex-word","title":"Multilingual and Cross-Lingual Complex Word Identification","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lexical-simplification-with-neural-ranking","title":"Lexical Simplification with Neural Ranking","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-lexical-simplification","title":"Understanding the Lexical Simplification Needs of Non-Native Speakers of English","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-ku-at-semeval-2016-task-11-word-embeddings","title":"AI-KU at SemEval-2016 Task 11: Word Embeddings and Substring Features for Complex Word Identification","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"amritacen-at-semeval-2016-task-11-complex","title":"AmritaCEN at SemEval-2016 Task 11: Complex Word Identification using Word Embedding","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coastalcph-at-semeval-2016-task-11-the","title":"CoastalCPH at SemEval-2016 Task 11: The importance of designing your Neural Networks right","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"garuda-bhasha-at-semeval-2016-task-11-complex","title":"Garuda \\& Bhasha at SemEval-2016 Task 11: Complex Word Identification Using Aggregated Learning Models","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hmc-at-semeval-2016-task-11-identifying","title":"HMC at SemEval-2016 Task 11: Identifying Complex Words Using Depth-limited Decision Trees","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iiit-at-semeval-2016-task-11-complex-word","title":"IIIT at SemEval-2016 Task 11: Complex Word Identification using Nearest Centroid Classification","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ju_nlp-at-semeval-2016-task-11-identifying","title":"JU\\_NLP at SemEval-2016 Task 11: Identifying Complex Words in a Sentence","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ltg-at-semeval-2016-task-11-complex-word","title":"LTG at SemEval-2016 Task 11: Complex Word Identification with Classifier Ensembles","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"macsaar-at-semeval-2016-task-11-zipfian-and","title":"MacSaar at SemEval-2016 Task 11: Zipfian and Character Features for ComplexWord Identification","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maza-at-semeval-2016-task-11-detecting","title":"MAZA at SemEval-2016 Task 11: Detecting Lexical Complexity Using a Decision Stump Meta-Classifier","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"melbourne-at-semeval-2016-task-11-classifying","title":"Melbourne at SemEval 2016 Task 11: Classifying Type-level Word Complexity using Random Forests with Corpus and Word List Features","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"plujagh-at-semeval-2016-task-11-simple-system","title":"PLUJAGH at SemEval-2016 Task 11: Simple System for Complex Word Identification","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pomona-at-semeval-2016-task-11-predicting","title":"Pomona at SemEval-2016 Task 11: Predicting Word Complexity Based on Corpus Frequency","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semeval-2016-task-11-complex-word","title":"SemEval 2016 Task 11: Complex Word Identification","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sensible-at-semeval-2016-task-11-neural","title":"Sensible at SemEval-2016 Task 11: Neural Nonsense Mangled in Ensemble Mess","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sv000gg-at-semeval-2016-task-11-heavy-gauge","title":"SV000gg at SemEval-2016 Task 11: Heavy Gauge Complex Word Identification with System Voting","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"taln-at-semeval-2016-task-11-modelling","title":"TALN at SemEval-2016 Task 11: Modelling Complex Words by Contextual, Lexical and Semantic Features","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"usaar-at-semeval-2016-task-11-complex-word","title":"USAAR at SemEval-2016 Task 11: Complex Word Identification with Sense Entropy and Sentence Perplexity","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uwb-at-semeval-2016-task-11-exploring","title":"UWB at SemEval-2016 Task 11: Exploring Features for Complex Word Identification","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-lexical-simplification-for-non","title":"Reliable Lexical Simplification for Non-Native Speakers","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"103a3a3d6a3b9fb425412572d1858afeb80ebe0a539714280034ffc3bec3d4a4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}