Print Email Facebook Twitter An Empirical Analysis of InCoder on the Statement Prediction Task Title An Empirical Analysis of InCoder on the Statement Prediction Task Author van der Heijden, Frank (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Izadi, M. (mentor) van Deursen, A. (mentor) Lukina, A. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-24 Abstract Automatic code completions are a widely used feature when programming code efficiently. These completions can be made by various code language models, and these can be differentiated in three categories: single token completion, statement (line) completion and block completions. These completions, and in particular statement predictions are usually created using only the left context, missing key information and context on the other side. InCoder, a novel state of the art model is capable of using both contexts. In this study we aim to show the impact of using both contexts in statement completions. The results show that on average, an improvement of 9.9% exact match and similar results for Edit Similarity, BLEU-4, ROUGE-L F1, and METEOR when using both contexts instead of only the left context. Subject code completionincoderstatement completionempirical analysis To reference this document use: http://resolver.tudelft.nl/uuid:69bb797f-4a62-4fef-afe8-1d9492b8d28e Part of collection Student theses Document type bachelor thesis Rights © 2022 Frank van der Heijden Files PDF main.pdf 543.13 KB Close viewer /islandora/object/uuid:69bb797f-4a62-4fef-afe8-1d9492b8d28e/datastream/OBJ/view