A hybrid Chinese word segmentation model for quality management-related texts based on transfer learning

Abstract

Text information mining is a key step to data-driven automatic/semi-automatic quality management (QM). For Chinese texts, a word segmentation algorithm is necessary for pre-processing since there are no explicit marks to define word boundaries. Because of intrinsic characteristics of QM-related texts, word segmentation algorithms for normal Chinese texts cannot be directly applied. Hence, based on the analysis of QM-related texts, we summarized six features, and proposed a hybrid Chinese word segmentation model by means of integrating transfer learning (TL), bidirectional long-short term memory (Bi-LSTM), multi-head attention (MA), and conditional random field (CRF) to construct the mTL-Bi-LSTM-MA-CRF model, considering insufficient samples of QM-related texts and excessive cutting of idioms. The mTL-Bi-LSTM-MA-CRF model is composed of two steps. Firstly, based on a word embedding space, the Bi-LSTM is introduced for context information learning, and the MA mechanism is selected to allocate attention among subspaces, and then the CRF is used to learn label sequence constraints. Secondly, a modified TL method is put forward for text feature extraction, adaptive layer weights learning, and loss function correction for selective learning. Experimental results show that the proposed model can achieve good word segmentation results with only a relatively small set of samples.

Quantitative Evaluation of Pharmaceutical Industry in Jilin Province Based on Text Mining

“…Hence, this paper adopts a manual approach to screen official websites to collect the After acquiring the original corpus, it is of great importance to firstly conduct data processing, i.e. text pre-processing, which includes word cut, removing stopwords, information cleaning and merging, etc., before carrying out the mining of the intrinsic information of the text [11]. In this paper, we employ word frequency analysis, keyword extraction, and LDA topic modelling to mine the intrinsic information of the text, extract key indicator variables, and refer to relevant references to construct a rather rigorous review system for pharmaceutical policies.…”