Main paper to be cited
@inproceedings{goo2018slot,
title={Slot-Gated Modeling for Joint Slot Filling and Intent Prediction},
author={Chih-Wen Goo and Guang Gao and Yun-Kai Hsu and Chih-Li Huo and Tsung-Chieh Chen and Keng-Wei Hsu and Yun-Nung Chen},
booktitle={Proceedings of The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
year={2018}
}
split your data into text file(seq.in), slot file(seq.out) and intent file(label)
following is default setting used by train.py
./data/
--train/
--seq.in
--seq.out
--label
--test/
--seq.in
--seq.out
--label
--valid/
--seq.in
--seq.out
--label
tensorflow 1.4
python 3.5
some sample usage
-
run with 32 units and no patience for early stop
python3 train.py --num_units=32 --patience=0 -
disable early stop and use intent attention version
python3 train.py --no_early_stop --model_type=intent_only -
use "python3 train.py -h" for all avaliable parameter settings