Affiliations: [a] Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
| [b] Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming, China
| [c] School of Foreign Languages, Yunnan University, Kunming, China
Abstract: It is of great significance to recognize the metallurgical entity relations in order to construct the Knowledge graph of Metallurgical Literature and to further understand the metallurgical literature. However, there are few researches on the textual entity relations in metallurgical fields either few marked Corpora. The syntactic structure of the same entity relationship category is relatively simple and has strong domain characteristics. The traditional entity relationship model can not identify the domain entity relationship well. Meanwhile the syntactic structure of the same entity relations class is relatively simple, and the syntactic structure is relatively simple in the recognition of entity relations in metallurgy field. Furthermore, the entities with similar syntactic structure often have the same entity relations and the different words in the sentence have different contribution to the entity relations. In order to solve the mentioned problems, this paper will combine the algorithm that can highlight the syntactic structure in sentences and improve the accuracy of the model with the Algorithm that can highlight the contribution of words in sentences and the loss function level integration is carried out in the framework of small sample prototype network, so as to maximize the advantages of each algorithm and improve the accuracy –firstly, in the coding layer of the prototype network, we use the CNN algorithm which can highlight the important words in the sentences and the TreeLSTM algorithm which can parse the sentences in the text so that the syntactic relations between the words in the sentences can be acted on in the relation recognition, the sentences are coded together by two algorithms, then, the EUCLIDEAN distance loss is calculated by using this high quality coding and the prototype coding, finally, the traditional entity relation recognition model with Attention Mechanism is integrated into the loss function, further highlighting the decisive role of important words in text sentences in relation recognition and improving the generalization of the model. The results showed that compared with the traditional methods such as CNN, RNN, PCNN and Bi-LSTM, the proposed method in this paper has better performance in the case of small sample data set.
