Sequence to Better Sequence: Continuous Revision of Combinatorial Structures

  title={Sequence to Better Sequence: Continuous Revision of Combinatorial Structures},
  author={Jonas Mueller and David Kenneth Gifford and Tommi S. Jaakkola},
We present a model that, after learning on observations of (sequence, outcome) pairs, can be efficiently used to revise a new sequence in order to improve its associated outcome. Our framework requires neither example improvements, nor additional evaluation of outcomes for proposed revisions. To avoid combinatorial-search over sequence elements, we specify a generative model with continuous latent factors, which is learned via joint approximate inference using a recurrent variational… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 19 extracted citations

QuaSE: Sequence Editing under Quantifiable Guidance

EMNLP • 2018
View 27 Excerpts
Highly Influenced

Incorporating Pseudo-Parallel Data for Quantifiable Sequence Editing

ArXiv • 2018
View 13 Excerpts
Method Support
Highly Influenced

Deep Headline Generation for Clickbait Detection

2018 IEEE International Conference on Data Mining (ICDM) • 2018
View 1 Excerpt
Method Support

Efficient Transfer Learning for Neural Network Language Models

2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) • 2018
View 1 Excerpt