{"id":"W2145908128","doi":"10.48550/arxiv.1412.6448","title":"Embedding Word Similarity with Neural Machine Translation","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Embedding; Natural language processing; Similarity (geometry); Machine translation; Artificial intelligence; Word (group theory); Word embedding; Translation (biology); Vocabulary; Example-based machine translation; German; Class (philosophy); Function (biology); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002304481,0.0002848565,0.0002886152,0.0001809516,0.0001449693,0.0001340488,0.001333251,0.0002087506,0.00001500342],"category_scores_gemma":[0.000009934208,0.0002969486,0.0001240598,0.000285629,0.00005111171,0.0003904585,0.0006502484,0.0006662391,0.00001288196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001004921,"about_ca_system_score_gemma":0.000080738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001583613,"about_ca_topic_score_gemma":0.0001086589,"domain_scores_codex":[0.9982335,0.0001336334,0.000168405,0.001040986,0.0001159058,0.0003075485],"domain_scores_gemma":[0.9983823,0.00008184283,0.0001782262,0.001142036,0.0000836936,0.0001318451],"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":[0.0000210477,0.00002261285,0.001698764,0.00004917796,0.00003004846,0.00008528245,0.0002051738,0.9787321,0.000007038936,0.01038592,0.00001127629,0.008751516],"study_design_scores_gemma":[0.0003847634,0.00002737964,0.0004171581,0.0000581982,0.00004017586,0.000005418449,0.000009377423,0.9919629,0.00001797772,0.006551431,0.0001873234,0.0003379458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2016463,0.00005400077,0.7964754,0.0002032798,0.0002789263,0.0001728812,0.0000036003,0.0002634634,0.00090213],"genre_scores_gemma":[0.9798293,0.00001571203,0.01970128,0.0001179514,0.00008014812,5.078195e-7,0.00001163936,0.00001590015,0.0002275389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.778183,"threshold_uncertainty_score":0.9999483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08227646160660891,"score_gpt":0.1993835748629519,"score_spread":0.117107113256343,"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."}}