# How to Train Your Agent to Read and Write

arXiv: https://arxiv.org/abs/2101.00916 · HTML: https://mlsanity.com/paper/2101.00916/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 4 Jan 2021.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network](https://mlsanity.com/paper/1712.02121/) (2017)
- [Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs](https://mlsanity.com/paper/1906.01195/) (2019)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [GraphGAN: Graph Representation Learning with Generative Adversarial Nets](https://mlsanity.com/paper/1711.08267/) (2017)
- [Location-aware Graph Convolutional Networks for Video Question Answering](https://mlsanity.com/paper/2008.09105/) (2020)
- [Generating Visually Aligned Sound from Videos](https://mlsanity.com/paper/2008.00820/) (2020)
- [PaperRobot: Incremental Draft Generation of Scientific Ideas](https://mlsanity.com/paper/1905.07870/) (2019)
- [Multi-marginal Wasserstein GAN](https://mlsanity.com/paper/1911.00888/) (2019)
- [SQL-to-Text Generation with Graph-to-Sequence Model](https://mlsanity.com/paper/1809.05255/) (2018)
- [Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2001.11003/) (2020)
- [Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning](https://mlsanity.com/paper/1908.05957/) (2019)
- [Text Understanding from Scratch](https://mlsanity.com/paper/1502.01710/) (2015)
- [Enhancing AMR-to-Text Generation with Dual Graph Representations](https://mlsanity.com/paper/1909.00352/) (2019)
- [Improving Generative Adversarial Networks with Local Coordinate Coding](https://mlsanity.com/paper/2008.00942/) (2020)
- [Adversarial Learning with Local Coordinate Coding](https://mlsanity.com/paper/1806.04895/) (2018)
- [Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2006.09242/) (2020)

## Built on by (most cited first, 2 of 2)

- [Towards Accurate Text-based Image Captioning with Content Diversity Exploration](https://mlsanity.com/paper/2105.03236/) (2021)
- [Exploring and Verbalizing Academic Ideas by Concept Co-occurrence](https://mlsanity.com/paper/2306.02282/) (2023)

## Abstract (arXiv)

Reading and writing research papers is one of the most privileged abilities that a qualified researcher should master. However, it is difficult for new researchers (egstudents) to fully grasp this ability. It would be fascinating if we could train an intelligent agent to help people read and summarize papers, and perhaps even discover and exploit the potential knowledge clues to write novel papers. Although there have been existing works focusing on summarizing (i.e., reading) the knowledge in a given text or generating (i.e., writing) a text based on the given knowledge, the ability of simultaneously reading and writing is still under development. Typically, this requires an agent to fully understand the knowledge from the given text materials and generate correct and fluent novel paragraphs, which is very challenging in practice. In this paper, we propose a Deep ReAder-Writer (DRAW) network, which consists of a textitReader that can extract knowledge graphs (KGs) from input paragraphs and discover potential knowledge, a graph-to-text textitWriter that generates a novel paragraph, and a textitReviewer that reviews the generated paragraph from three different aspects. Extensive experiments show that our DRAW network outperforms considered baselines and several state-of-the-art methods on AGENDA and M-AGENDA datasets. Our code and supplementary are released at https://github.com/menggehe/DRAW.