{"id":"W4385571623","doi":"10.18653/v1/2023.iwslt-1.27","title":"Learning Nearest Neighbour Informed Latent Word Embeddings to Improve Zero-Shot Machine Translation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Computer science; Machine translation; Artificial intelligence; Translation (biology); Sentence; Zero (linguistics); Word (group theory); Natural language processing; Security token; Exploit; Shot (pellet); Transfer of learning; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001117805,0.001038512,0.001176695,0.0007310845,0.000564105,0.00094982,0.001739377,0.001168033,0.003218035],"category_scores_gemma":[0.004454626,0.0004143932,0.000728895,0.001050806,0.0007588407,0.003021399,0.002301821,0.001712284,0.003203223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005035611,"about_ca_system_score_gemma":0.0007963455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002412211,"about_ca_topic_score_gemma":0.005578727,"domain_scores_codex":[0.9989023,0.0003608926,0.00006817561,0.0003353495,0.0002384517,0.00009482214],"domain_scores_gemma":[0.9987786,0.0004803326,0.00008560196,0.0003945332,0.0002088179,0.00005202103],"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":[0.0004858813,0.0005978819,0.001499693,0.000295993,0.0001986273,0.000330097,0.0004375242,0.1318014,0.03534968,0.01887343,0.01081765,0.7993121],"study_design_scores_gemma":[0.00005041327,0.0002771427,0.0004050401,0.00002140393,0.00004265847,0.000184961,0.0001208784,0.9519997,0.01528138,0.0285601,0.003021389,0.00003501903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07657599,0.001085298,0.9119049,0.0001975152,0.0001964729,0.00007222736,0.0002306814,0.006017082,0.003719771],"genre_scores_gemma":[0.6835267,0.000459471,0.3033101,0.0003179869,0.0001155835,0.0001440789,0.002397954,0.0005983224,0.00912962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003218035,"threshold_uncertainty_score":0.01076537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02237869540178276,"score_gpt":0.2963109933440271,"score_spread":0.2739322979422443,"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."}}