Program Synthesis

BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the unidirectionality constraint by using a masked language model (MLM) pre-training objective. The masked language model randomly masks some of the tokens from the input, and the objective is to predict the original vocabulary id of the masked word based only on its context. Unlike left-to-right language model pre-training, the MLM objective enables the representation to fuse the left and the right context, which allows us to pre-train a deep bidirectional Transformer. In addition to the masked language model, BERT uses a next sentence prediction task that jointly pre-trains text-pair representations. There are two steps in BERT: pre-training and fine-tuning. During pre-training, the model is trained on unlabeled data over different pre-training tasks. For fine-tuning, the BERT model is first initialized with the pre-trained parameters, and all of the parameters are fine-tuned using labeled data from the downstream tasks. Each downstream task has separate fine-tuned models, even though they are initialized with the same pre-trained parameters.

CodeGen is an autoregressive transformers with next-token prediction language modeling as the learning objective trained on a natural language corpus and programming language data curated from GitHub.

CuBERT, or Code Understanding BERT, is a BERT based model for code understanding. In order to achieve this, the authors curate a massive corpus of Python programs collected from GitHub. GitHub projects are known to contain a large amount of duplicate code. To avoid biasing the model to such duplicated code, authors perform deduplication using the method of Allamanis (2018). The resulting corpus has 7.4 million files with a total of 9.3 billion tokens (16 million unique).

Graph Finite-State Automaton, or GFSA, is a differentiable layer for learning graph structure that adds a new edge type (expressed as a weighted adjacency matrix) to a base graph. This layer can be trained end-to-end to add derived relationships (edges) to arbitrary graph-structured data based on performance on a downstream task.

Instruction Pointer Attention Graph Neural Network, or IPA-GNN, is a learning-interpreter neural network (LNN) based on GNNs for learning to execute programmes. It achieves improved systematic generalization on the task of learning to execute programs using control flow graphs. The model arises by considering RNNs operating on program traces with branch decisions as latent variables. The IPA-GNN can be seen either as a continuous relaxation of the RNN model or as a GNN variant more tailored to execution.

SpreadsheetCoder is a neural network architecture for spreadsheet formula prediction. It is a BERT-based model architecture to represent the tabular context in both row-based and column-based formats. A BERT encoder computes an embedding vector for each input token, incorporating the contextual information from nearby rows and columns. The BERT encoder is initialized from the weights pre-trained on English text corpora, which is beneficial for encoding table headers. To handle cell references, a two-stage decoding process is used inspired by sketch learning for program synthesis. The decoder first generates a formula sketch, which does not include concrete cell references, and then predicts the corresponding cell ranges to generate the complete formula