{"id":"W2596484740","doi":"10.18653/v1/e17-1006","title":"Learning Compositionality Functions on Word Embeddings for Modelling Attribute Meaning in Adjective-Noun Phrases","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universität Bielefeld; Bundesministerium für Bildung und Forschung; Atomic Energy of Canada Limited; Deutsche Forschungsgemeinschaft","keywords":"Principle of compositionality; Adjective; Computer science; Natural language processing; Artificial intelligence; Noun; Noun phrase; Specifier; Meaning (existential); Word (group theory); Linguistics; Psychology; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001509155,0.001384133,0.001027012,0.001466215,0.000568393,0.001743076,0.001307341,0.001371314,0.002803933],"category_scores_gemma":[0.007626635,0.0007748787,0.001522012,0.001497244,0.0008485649,0.006996593,0.002448427,0.002452483,0.001932701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008082873,"about_ca_system_score_gemma":0.0008367387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002844236,"about_ca_topic_score_gemma":0.006604979,"domain_scores_codex":[0.9992581,0.0003280987,0.00005915982,0.0002163098,0.00007805358,0.00006025299],"domain_scores_gemma":[0.9973897,0.001782665,0.0001472307,0.000289885,0.0002928197,0.00009766106],"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":[0.001015629,0.0005748192,0.01013874,0.0009126104,0.0004603402,0.0004698343,0.001739759,0.1725498,0.01873109,0.07702836,0.01199936,0.7043797],"study_design_scores_gemma":[0.00003488985,0.00008313944,0.0006403851,0.00005854635,0.00005303911,0.00005935998,0.0002043893,0.8886635,0.00228199,0.1061094,0.001789107,0.00002226127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1043802,0.001372254,0.888638,0.000513215,0.0001524064,0.0001011349,0.0007806619,0.002047549,0.002014626],"genre_scores_gemma":[0.6362031,0.001066175,0.353472,0.000259614,0.000169827,0.0003244624,0.004125502,0.0006730581,0.003706211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002844236,"threshold_uncertainty_score":0.009380043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04482606863531863,"score_gpt":0.3216821619894747,"score_spread":0.2768560933541561,"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."}}