SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.00916 · AAAI · 2021

How to Train Your Agent to Read and Write

Mingkui Tan, Li Liu, Qi Wu, Guanghui Xu, Mengge He

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 (e.g., students) 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 Reader that can extract knowledge graphs (KGs) from input paragraphs and discover potential knowledge, a graph-to-text Writer that generates a novel paragraph, and a Reviewer 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2101.00916")
get_code_for_paper("2101.00916")
have("2101.00916")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2101.00916.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2101.00916.svg)](https://syntology.ai/paper/2101.00916)

Connect an agent — have() is free.