{"id":"W3203338521","doi":"10.18653/v1/2021.emnlp-main.328","title":"Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Western Canada Research Grid; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Waypoint; Computer science; Task (project management); Human–computer interaction; Embodied cognition; Path (computing); Natural language; Work (physics); Measure (data warehouse); Metric (unit); Shortest path problem; Artificial intelligence; Multimedia; Programming language; Real-time computing; Engineering; Theoretical computer science; Database","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001229989,0.0002605593,0.0004338133,0.0001383935,0.0001489283,0.0002317611,0.0007892852,0.0001559829,0.00001162535],"category_scores_gemma":[0.001561126,0.0001927003,0.0001004442,0.0007765341,0.0001233186,0.0004354326,0.0005507428,0.000525122,0.000001772367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040568,"about_ca_system_score_gemma":0.00007817574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000150018,"about_ca_topic_score_gemma":0.00001434211,"domain_scores_codex":[0.9978101,0.0001658942,0.0005381184,0.0007474286,0.0003774822,0.0003609932],"domain_scores_gemma":[0.9986753,0.0005018642,0.0002943062,0.0002911235,0.0001597719,0.00007767023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003682004,0.0001605095,0.001671973,0.0002278211,0.000007340699,0.000006621366,0.01576307,0.00001783308,0.4991747,0.006088323,0.000006236454,0.4768388],"study_design_scores_gemma":[0.00189017,0.0001703519,0.02438025,0.001847337,0.0000330355,0.00004782879,0.009068174,0.4867206,0.4641786,0.01088793,0.0001040176,0.0006716737],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554206,0.003546801,0.03358014,0.00547829,0.0001473571,0.0007318463,0.000006478539,0.00006364192,0.001024921],"genre_scores_gemma":[0.6880661,0.00001122082,0.3114011,0.0003114289,0.00002891671,0.0000620965,0.000005809175,0.00001480376,0.00009858154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4867028,"threshold_uncertainty_score":0.785809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02622123682191114,"score_gpt":0.3976567197951307,"score_spread":0.3714354829732195,"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."}}