{"id":"W4404783428","doi":"10.18653/v1/2024.conll-1.1","title":"Words That Stick: Using Keyword Cohesion to Improve Text Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cohesion (chemistry); Segmentation; Natural language processing; Artificial intelligence; Information retrieval; Keyword search","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001634304,0.0001299314,0.000122456,0.0002574076,0.00007508176,0.0003660723,0.0004065439,0.00004090795,0.00004978538],"category_scores_gemma":[0.00001905798,0.0001087195,0.00006413509,0.0008063009,0.00001449304,0.000914527,0.0002790288,0.00008744913,0.0001193745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000164799,"about_ca_system_score_gemma":0.00004426945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004525695,"about_ca_topic_score_gemma":0.00001938957,"domain_scores_codex":[0.9988434,0.00002637508,0.0001686259,0.0004611286,0.0002883541,0.0002121219],"domain_scores_gemma":[0.9993585,0.000075215,0.00003198233,0.0004088945,0.00004222092,0.00008323046],"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":[0.000004348562,0.00003133943,0.0002830807,0.00003071385,0.00003383902,0.00002988374,0.0008484538,0.001009703,0.3232658,0.02988026,0.001569548,0.643013],"study_design_scores_gemma":[0.00006306055,0.00008110516,0.0001188825,0.00007855751,0.00002399939,0.00000720926,0.00009596195,0.6503332,0.33861,0.00796886,0.002337802,0.0002813808],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01320817,0.00008045846,0.9835671,0.0004386541,0.0002444324,0.000205796,7.785321e-7,0.0009683209,0.001286315],"genre_scores_gemma":[0.4897544,0.000006840869,0.5089337,0.0002707274,0.00003777343,0.00001128714,0.000001145553,0.000009464621,0.000974607],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6493235,"threshold_uncertainty_score":0.4433454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0256191780195542,"score_gpt":0.3269138498247393,"score_spread":0.3012946718051851,"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."}}