{"id":"W2978957403","doi":"10.5220/0008319301550162","title":"Vocab Learn: A Text Mining System to Assist Vocabulary Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word (group theory); Ranking (information retrieval); Vocabulary; Natural language processing; Knowledge base; Artificial intelligence; Set (abstract data type); Base (topology); Word lists by frequency; Information retrieval; tf–idf; Levenshtein distance; Zipf's law; Sentence; Linguistics; Mathematics; Term (time)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001646844,0.0016651,0.001011934,0.005079921,0.0005489923,0.001474925,0.002222828,0.0009723789,0.0122723],"category_scores_gemma":[0.009367153,0.0006787194,0.001020512,0.002401204,0.000326692,0.004963733,0.002366469,0.001036165,0.009660745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000739641,"about_ca_system_score_gemma":0.001460807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002641937,"about_ca_topic_score_gemma":0.006706394,"domain_scores_codex":[0.9989374,0.0002058007,0.000154409,0.0003829321,0.0002638463,0.00005550831],"domain_scores_gemma":[0.9968208,0.001716161,0.0002617813,0.0004601745,0.000623143,0.0001178646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006268065,0.0005405722,0.008515911,0.002575948,0.0002637289,0.0004663051,0.0006808789,0.006219792,0.02437194,0.005975682,0.2452613,0.7045012],"study_design_scores_gemma":[0.0006759116,0.001004915,0.007258417,0.0006808115,0.0004134146,0.001279509,0.000842583,0.3707559,0.08027621,0.03403411,0.5025257,0.0002525449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04345917,0.002834925,0.5071787,0.001247046,0.0005655432,0.00193855,0.108306,0.3183656,0.01610463],"genre_scores_gemma":[0.08589727,0.001232076,0.7021836,0.0009664682,0.0001891463,0.001648822,0.1897397,0.006152155,0.0119908],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0122723,"threshold_uncertainty_score":0.0410549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00754809350283542,"score_gpt":0.2425714208696261,"score_spread":0.2350233273667907,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}