{"id":"W1544240449","doi":"10.1007/3-540-45486-1_4","title":"Using Noun Phrase Heads to Extract Document Keyphrases","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":236,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Noun phrase; Automatic summarization; Natural language processing; Artificial intelligence; Phrase; Task (project management); Extractor; Head (geology); Noun; Proper noun; Information retrieval; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008015468,0.0008493769,0.0008659037,0.001818369,0.0003690381,0.0008799173,0.004735611,0.00032709,0.0001159118],"category_scores_gemma":[0.00007938177,0.0008105002,0.000266506,0.001410989,0.0004896864,0.001350065,0.001606442,0.0008389102,0.0001261041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009142265,"about_ca_system_score_gemma":0.0005884468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007533775,"about_ca_topic_score_gemma":0.0001077748,"domain_scores_codex":[0.9940944,0.00004985449,0.0008304117,0.002428661,0.00154484,0.001051825],"domain_scores_gemma":[0.9961856,0.0003098284,0.0003374068,0.002523535,0.0002373004,0.0004063031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008562523,0.00004396748,0.00001893735,0.00001500982,0.00001633165,0.0002275119,0.000368284,0.07397829,0.0008479581,0.009247679,0.00002827972,0.9151992],"study_design_scores_gemma":[0.000356848,0.0004476858,0.0000412519,0.001134824,0.00004616012,0.0002626024,2.445738e-7,0.4026644,0.01628928,0.5576288,0.01854985,0.002578116],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002024125,0.0005558684,0.9941915,0.0005267109,0.0005555977,0.000586416,0.000005567061,0.0004827605,0.002893188],"genre_scores_gemma":[0.07828948,0.000106027,0.9180698,0.002771928,0.0004111596,0.00001623614,0.000004402255,0.00005756747,0.0002733528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9126211,"threshold_uncertainty_score":0.9994346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02587671481000824,"score_gpt":0.3118338681191701,"score_spread":0.2859571533091619,"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."}}