The Code2Text Challenge: Text Generation in Source Libraries

Richardson, Kyle; Zarrieß, Sina; Kuhn, Jonas

doi:10.18653/v1/w17-3516

Cited by 7 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…identifier names can be extracted. Our scoping of our target problem is consistent with the problem definition in many papers on code summarization [1], [12], [13], [22], [25].…”

Section: Problem and Overviewmentioning

confidence: 88%

A Neural Model for Generating Natural Language Summaries of Program Subroutines

LeClair

Jiang

McMillan

2019

2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)

267

294

View full text Add to dashboard Cite

Source code summarization -creating natural language descriptions of source code behavior -is a rapidly-growing research topic with applications to automatic documentation generation, program comprehension, and software maintenance. Traditional techniques relied on heuristics and templates built manually by human experts. Recently, data-driven approaches based on neural machine translation have largely overtaken template-based systems. But nearly all of these techniques rely almost entirely on programs having good internal documentation; without clear identifier names, the models fail to create good summaries. In this paper, we present a neural model that combines words from code with code structure from an AST. Unlike previous approaches, our model processes each data source as a separate input, which allows the model to learn code structure independent of the text in code. This process helps our approach provide coherent summaries in many cases even when zero internal documentation is provided. We evaluate our technique with a dataset we created from 2.1m Java methods. We find improvement over two baseline techniques from SE literature and one from NLP literature.

show abstract

“…identifier names can be extracted. Our scoping of our target problem is consistent with the problem definition in many papers on code summarization [1], [12], [13], [22], [25].…”

Section: Problem and Overviewmentioning

confidence: 88%

A Neural Model for Generating Natural Language Summaries of Program Subroutines

LeClair

Jiang

McMillan

2019

2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE)

267

294

View full text Add to dashboard Cite

show abstract

“…4. Use Natural Language Generation techniques to translate the BF++ code automatically to a friendly humanreadable text description as in [43,44].…”

Section: Discussionmentioning

confidence: 99%

BF++: a language for general-purpose program synthesis

Härmä¹,

Petković²

2021

Preprint

View full text Add to dashboard Cite

Most state of the art decision systems based on Reinforcement Learning (RL) are data-driven black-box neural models, where it is often difficult to incorporate expert knowledge into the models or let experts review and validate the learned decision mechanisms. Knowledge-insertion and model review are important requirements in many applications involving human health and safety. One way to bridge the gap between data and knowledge driven systems is program synthesis: replacing a neural network that outputs decisions with one that generates decision-making code in some programming language. We propose a new programming language, BF++, designed specifically for neural program synthesis in a Partially Observable Markov Decision Process (POMDP) setting and generate programs for a number of standard OpenAI Gym benchmarks. Source code is available at https://github.com/vadim0x60/cibi

show abstract

“…Machine translation (Sutskever et al, 2014;Cho et al, 2014) and image captioning (You et al, 2016) are seen as typical conditional language modelling tasks. More sophisticated tasks include text abstractive summarization (Nallapati et al, 2017;Narayan et al, 2019) and simplification (Zhang and Lapata, 2017), generating textual comments to source code (Richardson et al, 2017) and dialogue modelling (Lowe et al, 2017). Structured data may act as a conditioning context as well.…”

Section: Related Workmentioning

confidence: 99%

A Single Example Can Improve Zero-Shot Data Generation

Burnyshev,

Malykh,

Bout

et al. 2021

Preprint

View full text Add to dashboard Cite

Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-ofdomain detection, require extensive and flexible datasets for experiments and evaluation. As collecting such datasets is time-and laborconsuming, we propose to use text generation methods to gather datasets. The generator should be trained to generate utterances that belong to the given intent. We explore two approaches to generating task-oriented utterances. In the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training. In the oneshot approach, the model is presented with a single utterance from a test intent. We perform a thorough automatic, and human evaluation of the dataset generated utilizing two proposed approaches. Our results reveal that the attributes of the generated data are close to original test sets, collected via crowd-sourcing.

show abstract

The Code2Text Challenge: Text Generation in Source Libraries

Cited by 7 publications

References 20 publications

A Neural Model for Generating Natural Language Summaries of Program Subroutines

A Neural Model for Generating Natural Language Summaries of Program Subroutines

BF++: a language for general-purpose program synthesis

A Single Example Can Improve Zero-Shot Data Generation

Contact Info

Product

Resources

About