{"id":"W2473104040","doi":"10.18653/v1/n16-1106","title":"DAG-Structured Long Short-Term Memory for Semantic Compositionality","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Principle of compositionality; Computer science; Natural language processing; Semantics (computer science); Artificial intelligence; Representation (politics); Sentence; Semantic memory; Term (time); Recurrent neural network; Sequence (biology); Theoretical computer science; Artificial neural network; Cognition; Programming language","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":[0.0001623983,0.00009065528,0.0001117227,0.00003430688,0.00008148585,0.00005751374,0.0005196012,0.00004134024,0.00005357439],"category_scores_gemma":[0.0000134961,0.00005856959,0.00006426613,0.00004794055,0.00002700189,0.0002949067,0.0001460439,0.0000304916,0.00001546573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003523218,"about_ca_system_score_gemma":0.00003144139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007183344,"about_ca_topic_score_gemma":0.00002674375,"domain_scores_codex":[0.9990936,0.00002329548,0.0001768823,0.000331577,0.0001724462,0.000202208],"domain_scores_gemma":[0.9992378,0.0001134322,0.00002647736,0.0004891728,0.00006644794,0.00006669299],"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":[0.00002776268,0.0001029383,0.03351223,0.0001345231,0.00009511533,0.00003018282,0.0004352944,0.0003075069,0.09416816,0.4591016,0.001987423,0.4100972],"study_design_scores_gemma":[0.003398865,0.00020856,0.3189493,0.0002684285,0.00005560115,0.0002501304,0.00002663678,0.3443133,0.1426803,0.1867129,0.001430695,0.0017052],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.122616,0.00001568965,0.8741609,0.001760626,0.0003201357,0.0001683361,0.000003762428,0.0001403609,0.0008141981],"genre_scores_gemma":[0.9082766,9.404916e-7,0.09062649,0.000286723,0.0001123899,0.00001314794,0.000002173127,0.00000486942,0.0006766382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7856606,"threshold_uncertainty_score":0.2388398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03229492923303824,"score_gpt":0.2803132316393437,"score_spread":0.2480183024063055,"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."}}