{"id":"W2109209896","doi":"","title":"Measuring Lexical Cohesion: Beyond Word Repetition","year":2014,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Cohesion (chemistry); Computer science; Vocabulary; Natural language processing; Antecedent (behavioral psychology); Noun phrase; Pronoun; Artificial intelligence; Linguistics; Phrase; Expression (computer science); Personal pronoun; Repetition (rhetorical device); Noun; Metric (unit); Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003249831,0.0000552608,0.00006830226,0.00003413086,0.00006711158,0.00007579501,0.0003258812,0.00003433963,0.00004586994],"category_scores_gemma":[0.00004680284,0.00004760945,0.00002881081,0.0000843636,0.00001016611,0.0002258975,0.0001313627,0.00006805313,0.0001234626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001722125,"about_ca_system_score_gemma":0.00001215996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001279437,"about_ca_topic_score_gemma":0.000006971192,"domain_scores_codex":[0.9992501,0.00003767996,0.0001218425,0.0002466474,0.0002052323,0.0001385358],"domain_scores_gemma":[0.9994234,0.00004252664,0.0000221805,0.0004195479,0.00003143087,0.00006095149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001523047,0.0000179928,0.0005035921,0.000007081134,0.000002589395,0.000003094549,0.0001168412,0.0003297109,0.001086571,0.766116,0.0006106011,0.2312044],"study_design_scores_gemma":[0.0003568696,0.00005344845,0.003821436,0.00003770603,0.00000336452,0.00002887544,0.00001203268,0.8679398,0.01090612,0.09427343,0.02227089,0.0002960106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01466715,0.00001087758,0.9268976,0.001660667,0.0002506177,0.00003249556,2.774373e-8,0.0002054677,0.05627508],"genre_scores_gemma":[0.8250325,0.00000121619,0.1733711,0.0005966526,0.000137475,0.000002831269,2.536225e-7,0.000002883153,0.0008550689],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8676101,"threshold_uncertainty_score":0.1941457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04119341609654793,"score_gpt":0.2294941727572702,"score_spread":0.1883007566607223,"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."}}