Template Controllable keywords-to-text Generation

TL;DR

This paper introduces a neural model for generating natural language text from unordered keywords and POS-based templates, enhancing controllability and surface realization in NLG systems.

Contribution

It presents a novel encode-attend-decode framework that uses weak supervision and is indifferent to keyword order, improving flexibility and performance in keywords-to-text generation.

Findings

Outperforms state-of-the-art baselines in various domains

Effective with weak supervision and automatic template generation

Indifferent to input keyword order

Abstract

This paper proposes a novel neural model for the understudied task of generating text from keywords. The model takes as input a set of un-ordered keywords, and part-of-speech (POS) based template instructions. This makes it ideal for surface realization in any NLG setup. The framework is based on the encode-attend-decode paradigm, where keywords and templates are encoded first, and the decoder judiciously attends over the contexts derived from the encoded keywords and templates to generate the sentences. Training exploits weak supervision, as the model trains on a large amount of labeled data with keywords and POS based templates prepared through completely automatic means. Qualitative and quantitative performance analyses on publicly available test-data in various domains reveal our system's superiority over baselines, built using state-of-the-art neural machine translation and controllable transfer techniques. Our approach is indifferent to the order of input keywords.