{"url":"/task/lexical-complexity-prediction","name":"Lexical Complexity Prediction","slug":"lexical-complexity-prediction","description_markdown":"Predicting the complexity of a word/multi-word expression in a sentence.","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":"derived"},"counts":{"papers_tagged":44,"papers_with_code":11,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/lexical-analysis","name":"Lexical Analysis"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":11,"of":11,"tagged_in_all":44,"items":[{"url":"/paper/japanese-lexical-complexity-for-non-native","title":"Japanese Lexical Complexity for Non-Native Readers: A New Dataset","date":"2023-06-30","arxiv_id":"2306.17399","repositories_listed":2,"syntology":null},{"url":"/paper/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","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","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/beyond-film-subtitles-is-youtube-the-best","title":"Beyond Film Subtitles: Is YouTube the Best Approximation of Spoken Vocabulary?","date":"2024-10-04","arxiv_id":"2410.03240","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-readability-assessment-of-german-1","title":"Automatic Readability Assessment of German Sentences with Transformer Ensembles","date":"2022-09-09","arxiv_id":"2209.04299","repositories_listed":1,"syntology":null},{"url":"/paper/andi-at-semeval-2021-task-1-predicting","title":"ANDI at SemEval-2021 Task 1: Predicting complexity in context using distributional models, behavioural norms, and lexical resources","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cs60075-team2-at-semeval-2021-task-1-lexical-1","title":"cs60075\\_team2 at SemEval-2021 Task 1 : Lexical Complexity Prediction using Transformer-based Language Models pre-trained on various text corpora","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/biggreen-at-semeval-2021-task-1-lexical","title":"BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models","date":"2021-04-19","arxiv_id":"2104.09040","repositories_listed":1,"syntology":null},{"url":"/paper/iitk-lcp-at-semeval-2021-task-1","title":"IITK@LCP at SemEval 2021 Task 1: Classification for Lexical Complexity Regression Task","date":"2021-04-02","arxiv_id":"2104.01046","repositories_listed":1,"syntology":null},{"url":"/paper/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}],"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}