# Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems

arXiv: https://arxiv.org/abs/1806.05484 · HTML: https://mlsanity.com/paper/1806.05484/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2018.

## Built on by (most cited first, 1 of 1)

- [Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users](https://mlsanity.com/paper/2110.13213/) (2021)

## Abstract (arXiv)

This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses. First, we learn features by using a deep learning architecture in which the weights for the unknown and known categories are jointly optimised. Second, an unsupervised method is used for further tuning the weights. Sharing weights injects prior knowledge to unknown categories. The unsupervised tuning (i.e. the risk minimisation) improves the F-Measure when recognising nearly zero-shot data on the DSTC3 corpus. This unsupervised method can be applied subject to two assumptions: the rank of the class marginal is assumed to be known and the class-conditional scores of the classifier are assumed to follow a Gaussian distribution.