Research on Domain Term Dictionary Construction Based on Chinese Wikipedia

Abstract

Domain terms are words or phrases that represent concepts or relationships in a specific domain. It can represent the characteristics of corresponding domains. The automatic construction of domain-specific dictionary is an important task in natural language processing, which can be adopted in domain-specific ontology construction, vertical search, text classification, information retrieval, question answering system etc. In this paper, we propose a novel method for constructing domain term dictionary based on Chinese Wikipedia web resource and deep learning technology. We for first time explore to word representation by Word2vec model integrating Wikipedia link structure. Then we use word clustering algorithm and seed word extraction method to construct an original domain dictionary. Moreover, neural network method is applied to extend domain dictionary. In experiments, different methods were employed to extract the domain-specific terms and their performances were compared in automobile field, the results reveal the effectiveness of our method for construction of domain-specific dictionary.

Exploiting Wikipedia to Measure the Semantic Relatedness between Arabic Terms

“…log(𝑁) (5) Where 𝑐𝑎𝑡𝐷𝑒𝑠𝑐𝑒𝑛𝑑𝑎𝑛𝑡𝑠𝐼𝑉(𝑐) is the information value of category 𝑐, des(c) is the number of descendants of category 𝑐 and 𝑁 is the set of all categories in Wikipedia. It is assumed that the category with a large number of descendants is more general and thus has less information value.…”

“…Due to this importance and popularity, many works have exploited Wikipedia as a knowledge source to measure the semantic relatedness between terms. Some of these works have exploited the structure of Wikipedia articles such as categories, hyperlinks, and templates [4,5]. Another line of works has attempted to measure similarity based on the natural language processing of the textual content of Wikipedia articles [6][7][8][9].…”

VDRF: Sensing the defect information to risk level of vehicle recall based on bert communication model

“…Embedding. Firstly,Word segmentation tool jieba [23] with the vehicle domain dictionary constructed in our previous published paper [24] is employed on the complaint text S. Then, the segmented complaint text S is vectorized in the embedding layer, which can reduce the input dimension and reduce the number of parameters of the neural network. Furthermore, the dense vector representation of the word vector layer can contain more semantic information [25].…”