{"id":"W3212549866","doi":"10.18653/v1/2021.findings-emnlp.214","title":"Novel Natural Language Summarization of Program Code via Leveraging Multiple Input Representations","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Automatic summarization; Programming language; Python (programming language); Source code; Code (set theory); Encoder; Redundant code; Code generation; Task (project management); Artificial intelligence; Natural language processing; Set (abstract data type); Operating system","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":[0.0007138365,0.001660027,0.0006497623,0.00165183,0.0003499158,0.0007868239,0.00138987,0.001023233,0.002051433],"category_scores_gemma":[0.00419336,0.0003562053,0.001200903,0.001028732,0.0004358322,0.002840607,0.001140487,0.001885803,0.001434821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007287251,"about_ca_system_score_gemma":0.001242762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003782955,"about_ca_topic_score_gemma":0.007115329,"domain_scores_codex":[0.9992078,0.0001988352,0.00004809564,0.0003178857,0.0001578265,0.00006956686],"domain_scores_gemma":[0.9983223,0.0006876244,0.0002176327,0.0002914048,0.0004055978,0.00007538231],"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":[0.0004140016,0.000417697,0.00295788,0.0007003314,0.0001375434,0.000455341,0.0005247299,0.0659845,0.06439424,0.005200919,0.02372059,0.8350922],"study_design_scores_gemma":[0.00003717845,0.0002658927,0.0015886,0.00004329159,0.00007809026,0.0002219594,0.000170205,0.9420617,0.03523741,0.009923287,0.01033537,0.00003716044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0600643,0.0009238039,0.9072844,0.0006105231,0.0001441495,0.0002376623,0.002566315,0.02614581,0.002022939],"genre_scores_gemma":[0.304722,0.0004989465,0.6661299,0.0004955325,0.0001494422,0.0004029461,0.01960693,0.001417111,0.006577106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003782955,"threshold_uncertainty_score":0.007521868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02481779938061277,"score_gpt":0.3109085428145918,"score_spread":0.2860907434339791,"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."}}