A Canonical Semi-Deterministic Transducer
Achilles Beros, Colin de la Higuera

TL;DR
This paper establishes a canonical form for semi-deterministic transducers, introduces a learning algorithm using translation queries, and proves limitations of learning with only domain knowledge.
Contribution
It provides the first canonical form for semi-deterministic transducers and an algorithm for their learning via translation queries.
Findings
Existence of a canonical form for semi-deterministic transducers.
Development of a learning algorithm using translation queries.
Proof that no learning algorithm exists using only domain knowledge.
Abstract
We prove the existence of a canonical form for semi-deterministic transducers with incomparable sets of output strings. Based on this, we develop an algorithm which learns semi-deterministic transducers given access to translation queries. We also prove that there is no learning algorithm for semi-deterministic transducers that uses only domain knowledge.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
