Luo Zhenquan

TL;DR: The BERT pre-training model is used for text classification in this article, where the added input layer is a feature representation layer for assisting classification and recognition, and the BERT model does not need to be improved by a Google company and the like.

TL;DR: In this article, a sequence labeling method and system and an event element extraction method are described, and the method comprises the steps: adding an input layer of a BERT pre-training model, enabling the BERT model to participate in the training, and carrying out the sequence labeling of a to-be-labeled text based on a classification model obtained after training, wherein the added input layer is a feature word representation layer for assisting classification and recognition.

TL;DR: In this article, the authors proposed an unsupervised text classification method and system, which comprises the steps: setting a seed keyword for each classification label, performing semantic similar word expansion on the seed keyword by adopting a pre-trained word vector to obtain an expanded keyword, encoding the seed keywords and the extended keywords into word vectors; converting the to-beclassified texts into text vectors; and classifying the text vectors based on the word vectors.

TL;DR: In this article, a word segmentation method consisting of constructing a dictionary, generating a prefix tree for the sentence to be segmented based on the dictionary and performing word graph scanning to generate a directed acyclic graph formed by all possible word forming conditions was proposed.

TL;DR: In this paper, a question-answering method was proposed, which comprises the steps: obtaining a natural query statement input by a user, and converting the natural query statements into a semantic symbol string; generating a semantic path corresponding to the natural queries according to the query statement and the semanticsymbol string; then, generating a machine query statement which can be recognized by a database for storing the knowledge graph; and finally, querying a question and answer result corresponding to machine query statements, and feeding back the result.