Abstract | Despite Chinese word segmentation being a specific case, MMTNN can be easily generalized and applied to other sequence labeling tasks. |
Introduction | Most previous systems address this problem by treating this task as a sequence labeling problem where each character is assigned a tag indicating its position in the word. |
Introduction | (2011) developed the SENNA system that approaches or surpasses the state-of-the-art systems on a variety of sequence labeling tasks for English. |
Introduction | 0 Despite Chinese word segmentation being a specific case, our approach can be easily generalized to other sequence labeling tasks. |
Max-Margin Tensor Neural Network | Despite tensor-based transformation being effective for capturing the interactions, introducing tensor-based transformation into neural network models to solve sequence labeling task is time prohibitive since the tensor product operation drastically slows down the model. |
Related Work | The most popular approach treats word segmentation as a sequence labeling problem which was first proposed in Xue (2003). |
Related Work | However, given the small size of their tensor matrix, they do not have the problem of high time cost and overfitting problem as we faced in modeling a sequence labeling task like Chinese word segmentation. |
Related Work | By introducing tensor factorization into the neural network model for sequence labeling tasks, the model training and inference are speeded up and overfitting is prevented. |
Introduction | While most previous work focus on in-domain sequential labelling or cross-domain classification tasks, we are the first to learn representations for web-domain structured prediction. |
Learning from Web Text | This may partly be due to the fact that unlike computer vision tasks, the input structure of POS tagging or other sequential labelling tasks is relatively simple, and a single nonlinear layer is enough to model the interactions within the input (Wang and Manning, 2013). |
Related Work | Regarding using neural networks for sequential labelling , our approach shares similarity with that of Collobert et al. |