Research Advances In Semantic Slot Filling
This repo mainly summary latest research advances on semantic slot filling.
Thank you pay attention to the repo and it will not be updated!
Note: these results from ATIS dataset.
|Model||F1 Score||Intent Accuracy||Year|
|Recursive NN||0.9396||0.954||Guo et al. 2014|
|Joint model with recurrent intent and slot label context||0.9447||0.984||Liu and Lane, 2016b|
|Joint model with recurrent slot label context||0.9464||0.984||Liu and Lane, 2016b|
|RNN with Label Sampling||0.9489||NA||Liu and Lane, 2015|
|Hybrid RNN||0.9506||NA||Mesnil et al., 2015|
|RNN-EM||0.9525||NA||Peng and Yao, 2015|
|CNN-CRF||0.9435||NA||Xu and Sarikaya, 2013|
|Encoder-labeler Deep LSTM||0.9566||NA||Kurata et al., 2016|
|Joint GRU model(W)||0.9549||0.9810||Zhang and Wang, 2016|
|Attention Encoder-Decoder NN||0.9587||0.9843||Liu and Lane, 2016a|
|Bi-model without a decoder||0.9665||0.9876||Wang and Shen, 2018|
|Bi-model with a decoder||0.9689||0.9899||Wang and Shen, 2018|
- Tur, Gokhan, Dilek Hakkani-Tür, and Larry Heck. "What is left to be understood in ATIS?." Spoken Language Technology Workshop (SLT), 2010 IEEE. IEEE, 2010.
- Yao, Kaisheng, et al. "Spoken language understanding using long short-term memory neural networks." Spoken Language Technology Workshop (SLT), 2014 IEEE. IEEE, 2014.
Vu, Ngoc Thang, et al. "Bi-directional recurrent neural network with ranking loss for spoken language understanding." Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. Ieee, 2016.
Zhu, Su, and Kai Yu. "Encoder-decoder with focus-mechanism for sequence labelling based spoken language understanding." 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017.
Wang, Yu, Yilin Shen, and Hongxia Jin. "A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling." Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). Vol. 2. 2018.