deploy: cceb6a3

Author: mallamanis

paper-abstracts.json

@@ -1 +1 @@
-[["wang2020cocogum", "CoCoGUM: Contextual Code Summarization with Multi-Relational GNN on UMLs"], ["haque2020improved", "Improved Automatic Summarization of Subroutines via Attention to File Context"], ["ye2020leveraging", "Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning"], ["fernandes2019structured", "Structured Neural Summarization"]]
+[["wang2020cocogum", "CoCoGUM: Contextual Code Summarization with Multi-Relational GNN on UMLs"], ["haque2020improved", "Improved Automatic Summarization of Subroutines via Attention to File Context"], ["ye2020leveraging", "Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning"], ["shido2019automatic", "Automatic Source Code Summarization with Extended Tree-LSTM"]]

papers.html

@@ -0,0 +1 @@
+[["fried2022incoder", "InCoder: A Generative Model for Code Infilling and Synthesis"], ["kocetkov2022stack", "The Stack: 3TB of permissively licensed source code"], ["mir2021manytypes4py", "ManyTypes4Py: A Benchmark Python Dataset for Machine Learning-based Type Inference"], ["bavarian2022efficient", "Efficient Training of Language Models to Fill in the Middle"]]

publications-metadata/ahmad2020transformer.json

@@ -1 +1 @@
-[["fried2022incoder", "InCoder: A Generative Model for Code Infilling and Synthesis"], ["li2022exploring", "Exploring Representation-Level Augmentation for Code Search"], ["deze2022bridging", "Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding"], ["bavishi2019autopandas", "AutoPandas: neural-backed generators for program synthesis"]]
+[["fried2022incoder", "InCoder: A Generative Model for Code Infilling and Synthesis"], ["li2022exploring", "Exploring Representation-Level Augmentation for Code Search"], ["allal2022santacoder", "SantaCoder: don\u2019t reach for the stars!"], ["deze2022bridging", "Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding"]]

publications-metadata/allal2022santacoder.json

@@ -1 +1 @@
-[["karampatsis2020scelmo", "SCELMo: Source Code Embeddings from Language Models"], ["rabin2020demystifying", "Towards Demystifying Dimensions of Source Code Embeddings"], ["cummins2020programl", "ProGraML: Graph-based Deep Learning for Program Optimization and Analysis"], ["bui2018hierarchical", "Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Code"]]
+[["karampatsis2020scelmo", "SCELMo: Source Code Embeddings from Language Models"], ["rabin2020demystifying", "Towards Demystifying Dimensions of Source Code Embeddings"], ["peng2021how", "How could Neural Networks understand Programs?"], ["cummins2020programl", "ProGraML: Graph-based Deep Learning for Program Optimization and Analysis"]]

publications-metadata/bavarian2022efficient.json

@@ -1 +1 @@
-[["tufano2020unit", "Unit Test Case Generation with Transformers"], ["glassman2015overcode", "OverCode: visualizing variation in student solutions to programming problems at scale"], ["doderlein2022piloting", "Piloting Copilot and Codex: Hot Temperature, Cold Prompts, or Black Magic?"], ["zhong2020semantic", "Semantic Scaffolds for Pseudocode-to-Code Generation"]]
+[["tufano2020unit", "Unit Test Case Generation with Transformers"], ["glassman2015overcode", "OverCode: visualizing variation in student solutions to programming problems at scale"], ["doderlein2022piloting", "Piloting Copilot and Codex: Hot Temperature, Cold Prompts, or Black Magic?"], ["nye2021program", "Program Synthesis with Large Language Models"]]

publications-metadata/bennun2018neural.json

@@ -1 +1 @@
-[["karampatsis2020scelmo", "SCELMo: Source Code Embeddings from Language Models"], ["tran2019recovering", "Recovering Variable Names for Minified Code with Usage Contexts"], ["wang2020blended", "Blended, precise semantic program embeddings"], ["allamanis2015suggesting", "Suggesting Accurate Method and Class Names"]]
+[["tran2019recovering", "Recovering Variable Names for Minified Code with Usage Contexts"], ["karampatsis2020scelmo", "SCELMo: Source Code Embeddings from Language Models"], ["wang2020blended", "Blended, precise semantic program embeddings"], ["allamanis2015suggesting", "Suggesting Accurate Method and Class Names"]]

publications-metadata/chen2022codet.json

@@ -1 +1 @@
-[["barone2017parallel", "A parallel corpus of Python functions and documentation strings for automated code documentation and code generation"], ["aggarwal2015using", "Using Machine Translation for Converting Python 2 to Python 3 Code"], ["gros2020code", "Code to Comment \"Translation\": Data, Metrics, Baselining & Evaluation"], ["loyola2018content", "Content Aware Source Code Change Description Generation"]]
+[["barone2017parallel", "A parallel corpus of Python functions and documentation strings for automated code documentation and code generation"], ["aggarwal2015using", "Using Machine Translation for Converting Python 2 to Python 3 Code"], ["gros2020code", "Code to Comment \"Translation\": Data, Metrics, Baselining & Evaluation"], ["roziere2021leveraging", "Leveraging Automated Unit Tests for Unsupervised Code Translation"]]

publications-metadata/chirkova2021embeddings.json

@@ -1 +1 @@
-[["brauckmann2020compiler", "Compiler-based graph representations for deep learning models of code"], ["cummins2020programl", "ProGraML: Graph-based Deep Learning for Program Optimization and Analysis"], ["chae2016automatically", "Automatically generating features for learning program analysis heuristics"], ["cummins2017synthesizing", "Synthesizing benchmarks for predictive modeling"]]
+[["brauckmann2020compiler", "Compiler-based graph representations for deep learning models of code"], ["chae2016automatically", "Automatically generating features for learning program analysis heuristics"], ["cummins2020programl", "ProGraML: Graph-based Deep Learning for Program Optimization and Analysis"], ["cummins2017synthesizing", "Synthesizing benchmarks for predictive modeling"]]