Biblio

Deep learning models rely on single word features and location features of text to achieve good results in text relation extraction tasks. However, previous studies have failed to make full use of semantic information contained in sentence dependency syntax trees, and data sparseness and noise propagation still affect classification models. The BERT(Bidirectional Encoder Representations from Transformers) pretrained language model provides a better representation of natural language processing tasks. And entity enhancement methods have been proved to be effective in relation extraction tasks. Therefore, this paper proposes a combination of the shortest dependency path and entity-enhanced BERT pre-training language model for model construction to reduce the impact of noise terms on the classification model and obtain more semantically expressive feature representation. The algorithm is tested on SemEval-2010 Task 8 English relation extraction dataset, and the F1 value of the final experiment can reach 0. 881.

With the rapid improvement of China's industrial production level, there are an increasing number of industrial enterprises and kinds of products. The quality and safety supervision of industrial products is an important step to ensure people's livelihood safety. The current supervision includes a number of processes, such as risk monitoring, public opinion analysis, supervision, spot check and postprocessing. The lack of effective information integration and sharing between the above processes cannot support the implementation of whole-chain regulation well. This paper proposes a whole-chain supervision method of industrial product quality and safety based on a knowledge graph, which integrates massive and complex data of the whole chain and visually displays the relationships between entities in the regulatory process. This method can effectively solve the problem of information islands and track and locate the quality problems of large-scale industrial products.

Distant supervision is a widely used data labeling method for relation extraction. While aligning knowledge base with the corpus, distant supervision leads to a mass of wrong labels which are defined as noise. The pattern-based denoising model has achieved great progress in selecting trustable sentences (instances). However, the writing of relation-specific patterns heavily relies on expert’s knowledge and is a high labor intensity work. To solve these problems, we propose a noise reduction framework, NOIR, to iteratively select trustable sentences with a little help of a human. Under the guidance of experts, the iterative process can avoid semantic drift. Besides, NOIR can help experts discover relation-specific tokens that are hard to think of. Experimental results on three real-world datasets show the effectiveness of the proposed method compared with state-of-the-art methods.