NCTU-NTUT at IJCNLP-2017 Task 2: Deep Phrase Embedding using bi-LSTMs for Valence-Arousal Ratings Prediction of Chinese Phrases

In this paper, a deep phrase embedding approach using bi-directional long shortterm memory (Bi-LSTM) neural networks is proposed to predict the valence-arousal ratings of Chinese phrases. It adopts a Chinese word segmentation frontend, a local order-aware word-, a global phrase-embedding representations and a deep regression neural network (DRNN) model. The performance of the proposed method was benchmarked on the IJCNLP 2017 shared task 2. According the official evaluation results, our system achieved mean rank 6.5 among all 24 submissions.