Chinese Spell Checking (CSC) task aims to detect and correct Chinese spelling errors.
A non-negligible shortcoming of the pre-defined context patterns is that they cannot be flexibly generalized to all kinds of semantic classes, and we call this phenomenon as "semantic sensitivity".
In addition, we propose the ProbExpan, a novel probabilistic ESE framework utilizing the entity representation obtained by the aforementioned language model to expand entities.
However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task.
This paper offers a comprehensive review of the research on Natural Language Generation (NLG) over the past two decades, especially in relation to data-to-text generation and text-to-text generation deep learning methods, as well as new applications of NLG technology.
In the GPU era, the locally and globally weighted summations are the current mainstreams, represented by the convolution and self-attention mechanism, as well as MLP.
Existing text- and image-based multimodal dialogue systems use the traditional Hierarchical Recurrent Encoder-Decoder (HRED) framework, which has an utterance-level encoder to model utterance representation and a context-level encoder to model context representation.
Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks.
We also provide a theoretical explanation of our method.