Bimodal Modelling of Source Code and Natural Language

By Miltiadis Allamanis, Daniel Tarlow, A. Gordon, Yi Wei. 2015

207 citations recorded by the source corpus.

Subfields: Natural Language Processing, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Multimodal Learning

Citations in the corpus

Evaluating Large Language Models Trained on Code (2021, methodology): “Later, Allamanis et al. (2015) applied this idea in text-to-code retrieval and Yin & Neu-big (2017) utilized it in text-conditional code generation.”
A Retrieve-and-Edit Framework for Predicting Structured Outputs (2018, background): “Code generation is well studied [21, 17, 4, 23, 1], but these approaches have not explored edit-based generation.”
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (2018, background): “These tasks parse natural language descriptions into a more general-purpose programming language such as Python (Allamanis et al., 2015; Ling et al., 2016; Rabinovich et al., 2017; Yin and Neu-big, 2017).”
CodeBLEU: a Method for Automatic Evaluation of Code Synthesis (2020, background): “As code artiﬁcial intelligence receives more and more attention (Allamanis et al. 2015; Yin and Neubig 2017; Al-lamanis et al. 2018; Monperrus 2018; Alon et al. 2019; Svyatkovskiy et al. 2020), the evaluation of code synthesis becomes critical to promote its development.”
PyMT5: Multi-mode Translation of Natural Language and Python Code with Transformers (2020, methodology): “While previous work (Allamanis et al., 2015; Yin and Neubig, 2017) has leveraged the grammar of code to extract features like the Ab-stract Syntax Tree for modeling (treating code and natural language as separate modalities), we follow examples like Barone and Sennrich (2017) and treat P YTHON and…”
code2seq: Generating Sequences from Structured Representations of Code (2018, methodology): “Following Allamanis et al. (2015a; 2016), we split code tokens into sub tokens; for example, a token with the value ArrayList , will be decomposed into Array and List .”
A Parallel Corpus of Python Functions and Documentation Strings for Automated Code Documentation and Code Generation (2017, methodology): “Other corpora have been assembled from user-generated descriptions matched to code fragments mined from public websites such as StackOverﬂow 2 (Allamanis et al., 2015b; Iyer et al., 2016) or IFTTT 3 (Quirk et al., 2015).”
Summarizing Source Code using a Neural Attention Model (2016, methodology): “We further use CODE-NN for code retrieval for programming related questions on a recent C# benchmark, and results show that CODE-NN improves the state of the art (Allamanis et al. (2015b)) for mean reciprocal rank (MRR) by a wide margin.”
A Convolutional Attention Network for Extreme Summarization of Source Code (2016, methodology): “(2015) aim to predict names and types of variables, whereas Allamanis et al.(2014) and Allamanis et al.(2015a) suggest names for variables, methods and classes. Similar to Allamanis et al.(2015a), we aim to predict method names but using only the tokens within a method and no other features (e.g.met”
Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow (2018, background): “Recent years have witnessed the burgeoning of a new suite of developer assistance tools based on natural language processing (NLP) techniques, for code completion [9], source code summarization [2], automatic documentation of source code [44], deobfuscation [16, 34, 40], cross-language porting [27, ”
code2vec: learning distributed representations of code (2018, methodology): “…analysis at all, has a wide range of applications: code2vec: Learning Distributed Representations of Code 1:5 predicting names for program entities [Allamanis et al. 2015a; Alon et al. 2018; Raychev et al. 2015], code completion [Mishne et al. 2012; Raychev et al. 2014], code summarization…”
Abstract Syntax Networks for Code Generation and Semantic Parsing (2017, background): “Allamanis et al. (2015) and Maddison and Tarlow (2014) proposed modeling code with a neural language model, generating concrete syntax trees in left-ﬁrst depth-ﬁrst order, focusing on metrics like perplexity and applications like code snippet retrieval.”
VirtualHome: Simulating Household Activities Via Programs (2018, background): “[4] retrieves code snippets from Stackoverflow based on language queries.”
JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation (2019, background): “…in the form of logical forms (Zettlemoyer and Collins, 2005), λ -DCS (Liang et al., 2013), regular expressions (Kushman and Barzilay, 2013; Locascio et al., 2016), database queries (Iyer et al., 2017; Zhong et al., 2017) and general purpose programs (Balog et al., 2016; Allamanis et al., 2015).”
Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code (2020, background): “Precise scoring of code fragments is essential for tasks such as translating a program from one programming language to another [54, 66], code completion [32, 76], and code synthesis from natural language and vice versa [7, 27, 67, 73].”
Semantic Scaffolds for Pseudocode-to-Code Generation (2020, methodology): “…tasks have typically employed sequence-based models (Ling et al., 2016) that do not account for structure on the output side, or tree-based models (Allamanis et al., 2015; Rabinovich et al., 2017a; Yin and Neubig, 2017; Hayati et al., 2018; Iyer et al., 2019) that incorporate the syntax but not…”
Structural Language Models of Code (2019, methodology): “Any-Code Completion: Java We take the Java-small dataset of Alon et al. (2019a), which is a re-split of the dataset of Allamanis et al.”