{"id":"W1657275562","doi":"","title":"Cross-Lingual Distributional Profiles of Concepts for Measuring Semantic Distance","year":2007,"lang":"en","type":"article","venue":"TUbilio (Technical University of Darmstadt)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Bootstrapping (finance); Natural language processing; WordNet; Artificial intelligence; Semantic similarity; Task (project management); Word (group theory); Distributional semantics; Lexicon; Ranking (information retrieval); Linguistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0008795983,0.0001413002,0.0002941707,0.0001140395,0.0001559299,0.00002337909,0.00123673,0.0001418655,0.00001334453],"category_scores_gemma":[0.0003348422,0.000146654,0.0001616413,0.00034196,0.0005533747,0.0003810819,0.0003833978,0.0001999156,0.000001128955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001317593,"about_ca_system_score_gemma":0.0001375117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000421062,"about_ca_topic_score_gemma":0.00003162973,"domain_scores_codex":[0.9985689,0.00002759884,0.0003094794,0.0003845968,0.0004007081,0.0003087061],"domain_scores_gemma":[0.9983999,0.0003314635,0.0002672672,0.0004340404,0.0004774205,0.00008987814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007708282,0.0006842687,0.01225737,0.001083276,0.00008290065,0.0001131811,0.0008082755,0.00004686522,0.1988291,0.7445492,0.0005560161,0.04021873],"study_design_scores_gemma":[0.001793184,0.0005005084,0.01048669,0.0004835485,0.00005454953,0.00003863967,0.0002265533,0.001417471,0.9413759,0.04012473,0.002839138,0.0006590862],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1037313,0.0003312616,0.8948624,0.0001032396,0.0000505194,0.0003012097,0.00007647555,0.0002973267,0.0002462653],"genre_scores_gemma":[0.7478266,0.00000415027,0.2520541,0.000009255144,0.00001597989,3.974944e-7,0.00001273484,0.000005188424,0.00007158779],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7425468,"threshold_uncertainty_score":0.5980374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174102123637127,"score_gpt":0.2928284967007948,"score_spread":0.2754182843370821,"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."}}