• Citations Per Year
Learn More
In this paper, we empirically explore the effects of various kinds of skip connections in stacked bidirectional LSTMs for sequential tagging. We investigate three kinds of skip connections connecting to LSTM cells: (a) skip connections to the gates, (b) skip connections to the internal states and (c) skip connections to the cell outputs. We present(More)
In this study, the effects of temperature-shift (from 30 to 25 °C) and temperature-constant (at 30 °C) cultivation on the mass of Monascus fuliginosus CG-6 mycelia and concentration of the produced monacolin K (MK) were monitored. The expression levels of the MK biosynthetic genes of M. fuliginosus CG-6 at constant and variable culture temperatures were(More)
This paper presents our system for the CIPS-SIGHAN-2014 bakeoff task of Simplified Chinese Parsing (Task 3). The system adopts a generative model with OOV prediction model. The former has a PCFG form while the latter uses a three-layer hierarchical Bayesian model. The final performance on the test corpus is reported together with the performance of the OOV(More)
Deep stacked RNNs are usually hard to train. Adding shortcut connections across different layers is a common way to ease the training of stacked networks. However, extra shortcuts make the recurrent step more complicated. To simply the stacked architecture, we propose a framework called shortcut block, which is a marriage of the gating mechanism and(More)
Named Entity Recognition (NER) is a tough task in Chinese social media due to a large portion of informal writings. Existing research uses only limited in-domain annotated data and achieves low performance. In this paper, we utilize both limited in-domain data and enough out-of-domain data using a domain adaptation method. We propose a multichannel LSTM-CRF(More)
  • 1