Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

4-2021

Abstract

Pretrained using large amount of data, autoregressive language models are able to generate high quality sequences. However, these models do not perform well under hard lexical constraints as they lack fine control of content generation process. Progressive insertion-based transformers can overcome the above limitation and efficiently generate a sequence in parallel given some input tokens as constraint. These transformers however may fail to support hard lexical constraints as their generation process is more likely to terminate prematurely. The paper analyses such early termination problems and proposes the ENtity-CONstrained insertion TransformER (ENCONTER), a new insertion transformer that addresses the above pitfall without compromising much generation efficiency. We introduce a new training strategy that considers predefined hard lexical constraints (e.g., entities to be included in the generated sequence). Our experiments show that ENCONTER outperforms other baseline models in several performance metrics rendering it more suitable in practical applications.

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

EACL 2021: Proceedings of the 16th European Chapter of the Association for Computational Linguistics, April 19-23, Kyiv, Ukraine and Virtual

First Page

1

Last Page

10

Publisher

ACL

City or Country

Stroudsburg, PA

Embargo Period

4-15-2021

Copyright Owner and License

LARC and Authors

Comments

Code is available at https://github.com/LARC-CMU-SMU/Enconter

Share

COinS