{"id":"W2604207308","doi":"10.1609/aaai.v31i1.10973","title":"Disambiguating Spatial Prepositions Using Deep Convolutional Networks","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Feature (linguistics); Natural language processing; Word (group theory); Deep learning; Set (abstract data type); Feature engineering; Pattern recognition (psychology); Linguistics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009241739,0.0001456259,0.0002048684,0.00007700424,0.004239624,0.0005132285,0.001024199,0.0001044627,0.0001032304],"category_scores_gemma":[0.001268518,0.0001211579,0.0001286792,0.0001886632,0.001412686,0.0005742072,0.0002554589,0.0002119738,0.00002446193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007763896,"about_ca_system_score_gemma":0.0001115494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005058545,"about_ca_topic_score_gemma":0.001375125,"domain_scores_codex":[0.9982492,0.0000239366,0.0005372111,0.0002213691,0.0006140163,0.0003542661],"domain_scores_gemma":[0.9975536,0.00008545322,0.0009347136,0.0002138581,0.001136426,0.00007591835],"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":[0.00002675156,0.00004731187,0.01030037,0.00001571827,0.00002935096,1.263124e-7,0.008628761,0.0004554221,0.0007672608,0.9719276,0.00002825725,0.007773106],"study_design_scores_gemma":[0.0001618284,0.0002091469,0.03570154,0.001580778,0.0001676479,0.000009884313,0.0727769,0.5124603,0.02128408,0.3539348,0.0005713869,0.001141712],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6387913,0.00005272848,0.048726,0.006682404,0.003019051,0.00161073,0.00001935252,0.0001628417,0.3009356],"genre_scores_gemma":[0.9989772,0.000022089,0.0004464299,0.00005487242,0.0003004972,0.00002604421,5.474283e-7,0.000007200472,0.000165102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6179928,"threshold_uncertainty_score":0.9970567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1385655047278296,"score_gpt":0.3622023285665965,"score_spread":0.2236368238387669,"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."}}