Open-Domain Name Error Detection using a Multi-Task RNN
2015pp. 737–746
Citations Over TimeTop 10% of 2015 papers
Abstract
Out-of-vocabulary name errors in speech recognition create significant problems for downstream language processing, but the fact that they are rare poses challenges for automatic detection, particularly in an open-domain scenario. To address this problem, a multi-task recurrent neural network language model for sentence-level name detection is proposed for use in combination with out-of-vocabulary word detection. The sentence-level model is also effective for leveraging external text data. Experiments show a 26% improvement in name-error detection F-score over a system using n-gram lexical features.
Related Papers
- → Gated Feedback Recurrent Neural Networks(2015)416 cited
- Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network(2019)
- → A Study on Performance Improvement of Recurrent Neural Networks Algorithm using Word Group Expansion Technique(2022)