# Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism

## TL;DR

The paper proposes the Scratchpad Mechanism, a new neural network component that enhances natural language generation by allowing the decoder to use encoder outputs as a memory, improving fluency across multiple tasks.

## Contribution

It introduces the Scratchpad Mechanism, enabling decoders to write to all encoder layers, which improves fluency and performance in seq2seq models for various NLG tasks.

## Key findings

- Achieved state-of-the-art results in machine translation, question generation, and summarization.
- Demonstrated improved fluency and expressiveness through qualitative assessments.
- Validated the effectiveness of Scratchpad across multiple datasets.

## Abstract

We introduce the Scratchpad Mechanism, a novel addition to the sequence-to-sequence (seq2seq) neural network architecture and demonstrate its effectiveness in improving the overall fluency of seq2seq models for natural language generation tasks. By enabling the decoder at each time step to write to all of the encoder output layers, Scratchpad can employ the encoder as a "scratchpad" memory to keep track of what has been generated so far and thereby guide future generation. We evaluate Scratchpad in the context of three well-studied natural language generation tasks --- Machine Translation, Question Generation, and Text Summarization --- and obtain state-of-the-art or comparable performance on standard datasets for each task. Qualitative assessments in the form of human judgements (question generation), attention visualization (MT), and sample output (summarization) provide further evidence of the ability of Scratchpad to generate fluent and expressive output.