Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-3

Comment Generation

3260 papers • 126 benchmarks • 313 datasets

Article commenting poses new challenges for machines, as it involves multiple cognitive abilities: understanding the given article, formulating opinions and arguments, and organizing natu ral language for expression.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in comment-generation-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find comment-generation-3 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

InCoder: A Generative Model for Code Infilling and Synthesis

Sida I. Wang, Wen-tau Yih, Luke Zettlemoyer, M. Lewis, Ruiqi Zhong, Daniel Fried, Freda Shi, Armen Aghajanyan, Jessy Lin, Eric Wallace•Mon Apr 11 2022

InCoder is introduced, a unified generative model that can perform program synthesis (via left-to-right generation) as well as editing (via infilling) with the ability to condition on bidirectional context substantially improves performance on these tasks, while still performing comparably on standard program synthesis benchmarks.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

818

0

Code Attention: Translating Code to Comments by Exploiting Domain Features

Ming Li, Hong-Yu Zhou, Jianxin Wu, Wenhao Zheng•Thu Sep 21 2017

A new attention module called Code Attention is proposed to translate code to comments, which is able to utilize the domain features of code snippets, such as symbols and identifiers, which has better performance over existing approaches in both BLEU and METEOR.

20 0

Automating code review activities by large-scale pre-training

Shuai Lu, Daya Guo, Nan Duan, Neel Sundaresan, Shengyu Fu, Zhiyu Li, Shailesh Jannu, Grant Jenks, Deep Majumder, Jared Green, Alexey Svyatkovskiy•Wed Mar 16 2022

This research proposes CodeReviewer, a pre-trained model that utilizes four pre-training tasks tailored specifically for the code review scenario, and establishes a high-quality benchmark dataset based on the collected data for these three tasks.

224 0

CoNT: Contrastive Neural Text Generation

Xipeng Qiu, Lingpeng Kong, Kai Lv, Xuanjing Huang, Chen An, Jiangtao Feng•Sat May 28 2022

Experimental results show that CoNT clearly outperforms the conventional training framework on all the ten benchmarks with a convincing margin, and achieves new state-of-the-art on summarization, code comment generation (without external data) and data-to-text generation.

35 0

Cross-Modal Commentator: Automatic Machine Commenting Based on Cross-Modal Information

Xu Sun, Lei Li, Pengcheng Yang, Zhihan Zhang, Fuli Luo, Chengyang Huang•Sun Jun 30 2019

This work proposes a new task: cross-model automatic commenting (CMAC), which aims to make comments by integrating multiple modal contents, and presents an effective co-attention model to capture the dependency between textual and visual information.

14 0

Automatic Generation of Personalized Comment Based on User Profile

Pengcheng Yang, Lei Li, Wenhuan Zeng, Abulikemu Abuduweili•Sun Jun 30 2019

Experimental results show that the proposed Personalized Comment Generation Network (PCGN), which utilizes user feature embedding with a gated memory and attends to user description to model personality of users, can generate natural, human-like and personalized comments.

27 0

MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models

Dongwon Lee, Thai Le, Suhang Wang•Mon Aug 31 2020

Malcom, an end-to-end adversarial comment generation framework, is developed that can successfully mislead five of the latest neural detection models to always output targeted real and fake news labels.

71 0

Retrieve and Refine: Exemplar-Based Neural Comment Generation

Bolin Wei•Tue Oct 22 2019

This work proposes to use the existing comments of similar source code as exemplars to guide the comment generation process, based on an open source search engine, and demonstrates that this model significantly outperforms the state-of-the-art methods.

135 0

Learning with Contrastive Examples for Data-to-Text Generation

Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, I. Kobayashi, Yusuke Miyao, Hiroya Takamura, Kasumi Aoki, Keiichi Goshima•Mon Nov 30 2020

Experiments on the market comment generation task show that exploiting contrastive examples improves the capability of generating sentences with better lexical choice, without degrading the fluency.

19 0

Adding a benchmark result helps the community track progress.

Comment Generation | State-of-the-Art