SentBS: Sentence-level Beam Search for Controllable Summarization

by   Chenhui Shen, et al.

A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods have limited effectiveness in enforcing the desired structure. To address this limitation, we propose a sentence-level beam search generation method (SentBS), where evaluation is conducted throughout the generation process to select suitable sentences for subsequent generations. We experiment with different combinations of decoding methods to be used as subcomponents by SentBS and evaluate results on the structure-controlled dataset MReD. Experiments show that all explored combinations for SentBS can improve the agreement between the generated text and the desired structure, with the best method significantly reducing the structural discrepancies suffered by the existing model, by approximately 68


page 1

page 2

page 3

page 4


MReD: A Meta-Review Dataset for Controllable Text Generation

When directly using existing text generation datasets for controllable g...

CUT: Controllable Unsupervised Text Simplification

In this paper, we focus on the challenge of learning controllable text s...

Sequentially Controlled Text Generation

While GPT-2 generates sentences that are remarkably human-like, longer d...

Unsupervised Controllable Text Generation with Global Variation Discovery and Disentanglement

Existing controllable text generation systems rely on annotated attribut...

Summarization with Precise Length Control

Many applications of text generation such as summarization benefit from ...

Topic-Aware Evaluation and Transformer Methods for Topic-Controllable Summarization

Topic-controllable summarization is an emerging research area with a wid...

Advancements in Scientific Controllable Text Generation Methods

The previous work on controllable text generation is organized using a n...

Please sign up or login with your details

Forgot password? Click here to reset