Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction
원문 초록
Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled sequence transduction with semi-supervised learning. The generative model can use neural networks to handle both discrete and continuous latent variables to exploit various features of data. Experiments show that our model provides not only a powerful supervised framework but also can effectively take advantage of the unlabeled data. On the SIGMORPHON morphological inflection benchmark, our model outperforms single-model state-of-art results by a large margin for the majority of languages.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Can a Neural Model Guide Fieldwork? A Case Study on Morphological Data Collection
OOVs in the Spotlight: How to Inflect them?
Morphological Inflection with Phonological Features
An Investigation of Noise in Morphological Inflection
Morphological Inflection: A Reality Check
Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.