{"id":"W4385570592","doi":"10.18653/v1/2023.americasnlp-1.7","title":"Fine-tuning Sentence-RoBERTa to Construct Word Embeddings for Low-resource Languages from Bilingual Dictionaries","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Word (group theory); Natural language processing; Sentence; Artificial intelligence; German; Construct (python library); Bilingual dictionary; Resource (disambiguation); Word embedding; Cluster analysis; Encoding (memory); Embedding; Similarity (geometry); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001715264,0.001559804,0.0007223265,0.001237676,0.0004333007,0.001477918,0.001267439,0.0007081568,0.004844789],"category_scores_gemma":[0.007191929,0.0005141344,0.00119268,0.001235365,0.0005351084,0.005043377,0.002410132,0.00252194,0.005478054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005991152,"about_ca_system_score_gemma":0.0009487899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002408691,"about_ca_topic_score_gemma":0.006860872,"domain_scores_codex":[0.9989483,0.0003895922,0.0001131712,0.0003751216,0.0001090285,0.00006484002],"domain_scores_gemma":[0.9980696,0.0007784111,0.000100236,0.0005867054,0.0003803183,0.00008475733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004386475,0.0006690145,0.0108477,0.0007690622,0.0003686093,0.0001789403,0.0009638817,0.05191262,0.03390027,0.01827888,0.02672419,0.8549482],"study_design_scores_gemma":[0.0001198557,0.0004055424,0.002794625,0.0001044123,0.0001319696,0.000413693,0.0008707663,0.9147359,0.02638831,0.03078421,0.02317647,0.00007428738],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1339476,0.0008770704,0.83983,0.000467773,0.0003488013,0.0003545601,0.002156593,0.01547202,0.006545556],"genre_scores_gemma":[0.3804068,0.0004273072,0.6003024,0.0004346886,0.00005968891,0.0006105764,0.01017714,0.001471154,0.006110209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004844789,"threshold_uncertainty_score":0.0162074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01355784174216233,"score_gpt":0.2914919215342536,"score_spread":0.2779340797920912,"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."}}