{"id":"W2170657549","doi":"10.18653/v1/s15-1001","title":"Neural Networks for Integrating Compositional and Non-compositional Sentiment in Sentiment Composition","year":2015,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"Treebank; Computer science; Composition (language); Sentiment analysis; Artificial intelligence; Process (computing); Artificial neural network; Principle of compositionality; Natural language processing; Parsing; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001803624,0.0007597498,0.0004166216,0.0007479026,0.0004826128,0.001082305,0.0007753068,0.0007976069,0.001759849],"category_scores_gemma":[0.004168104,0.0004937522,0.0006905608,0.0006467165,0.0006707464,0.003002664,0.0009934225,0.001464198,0.0005454489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009417632,"about_ca_system_score_gemma":0.000491274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002327056,"about_ca_topic_score_gemma":0.004429273,"domain_scores_codex":[0.9994356,0.0002125512,0.00003856188,0.0001253538,0.0001372755,0.00005059722],"domain_scores_gemma":[0.9993129,0.0003173442,0.0001126763,0.00006245248,0.0001661524,0.00002840034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003279832,0.0002148913,0.005549036,0.000222997,0.0002971162,0.0001438019,0.0004888248,0.5383201,0.02757752,0.07161962,0.003744545,0.3514936],"study_design_scores_gemma":[0.000006910756,0.00002376913,0.0003864435,0.00001217724,0.00002988528,0.00001384018,0.00001892653,0.9745336,0.002580215,0.02131232,0.00107251,0.000009430051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05258101,0.0004284401,0.9403489,0.0005618208,0.00007415439,0.00008452286,0.00007787606,0.000547213,0.005296077],"genre_scores_gemma":[0.6994835,0.0004787715,0.2941983,0.0002627919,0.0001127094,0.0001449279,0.0002542533,0.0001237693,0.004940884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002327056,"threshold_uncertainty_score":0.009538591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0236320803186479,"score_gpt":0.277199808752499,"score_spread":0.2535677284338511,"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."}}