Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding
| Autor: | Grégoire Mesnil, Li Deng, Dilek Hakkani-Tur, Gokhan Tur, Yann N. Dauphin, Geoffrey Zweig, Yoshua Bengio, Kaisheng Yao, Xiaodong He, Larry Heck, Dong Yu |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Conditional random field
Word embedding Acoustics and Ultrasonics Artificial neural network business.industry Computer science Time delay neural network Machine learning computer.software_genre Computational Mathematics Recurrent neural network Computer Science (miscellaneous) Benchmark (computing) Theano Artificial intelligence Electrical and Electronic Engineering business computer Spoken language |
| Zdroj: | IEEE/ACM Transactions on Audio, Speech, and Language Processing. 23:530-539 |
| ISSN: | 2329-9304 2329-9290 |
| DOI: | 10.1109/taslp.2014.2383614 |
| Popis: | Semantic slot filling is one of the most challenging problems in spoken language understanding (SLU). In this paper, we propose to use recurrent neural networks (RNNs) for this task, and present several novel architectures designed to efficiently model past and future temporal dependencies. Specifically, we implemented and compared several important RNN architectures, including Elman, Jordan, and hybrid variants. To facilitate reproducibility, we implemented these networks with the publicly available Theano neural network toolkit and completed experiments on the well-known airline travel information system (ATIS) benchmark. In addition, we compared the approaches on two custom SLU data sets from the entertainment and movies domains. Our results show that the RNN-based models outperform the conditional random field (CRF) baseline by 2% in absolute error reduction on the ATIS benchmark. We improve the state-of-the-art by 0.5% in the Entertainment domain, and 6.7% for the movies domain. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|