Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data
This work addresses SLU for applications like voice assistants by incrementally enhancing semi-supervised learning with unaligned data.
The paper tackled the problem of Spoken Language Understanding (SLU) on unaligned data by proposing a graph-based semi-supervised Conditional Random Fields (CRF) approach, which significantly improved the performance of the supervised model by utilizing knowledge from the graph, though no concrete numbers were provided.
We experiment graph-based Semi-Supervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data. The aligned labels for examples are obtained using IBM Model. We adapt a baseline semi-supervised CRF by defining new feature set and altering the label propagation algorithm. Our results demonstrate that our proposed approach significantly improves the performance of the supervised model by utilizing the knowledge gained from the graph.