{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009155802,0.001521364,0.001066596,0.003511175,0.0008695604,0.001555711,0.001007071,0.0009391942,0.005657888],"category_scores_gemma":[0.007017183,0.0004789899,0.0007921786,0.002805572,0.0007426419,0.004491306,0.002578201,0.001335084,0.004426281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004862179,"about_ca_system_score_gemma":0.0008196993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002438576,"about_ca_topic_score_gemma":0.003717177,"domain_scores_codex":[0.9988198,0.0001960697,0.0001094124,0.0005140818,0.0002451737,0.0001154988],"domain_scores_gemma":[0.996485,0.001199574,0.0005192501,0.0008035559,0.0007134468,0.0002791392],"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":[0.001712764,0.0003195477,0.006747995,0.0005445477,0.0001839375,0.0003185683,0.001769033,0.009413738,0.1039812,0.003020513,0.01882098,0.8531672],"study_design_scores_gemma":[0.0006042719,0.003467825,0.03530513,0.0002616526,0.0009824262,0.001404442,0.003608269,0.5619767,0.2816775,0.04268206,0.06769194,0.0003377633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3782445,0.004648749,0.560216,0.0007466376,0.0008885019,0.0004393972,0.00284653,0.04358659,0.008383079],"genre_scores_gemma":[0.6651645,0.0004943707,0.315567,0.0003732838,0.0003663296,0.0002296224,0.0073703,0.003763796,0.006670658],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005657888,"threshold_uncertainty_score":0.01892751,"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."}}