With the rapid development of artificial intelligence technology, semantic recognition technology is becoming more and more mature, providing the preconditions for the development of natural language to SQL (NL2SQL) technology. In the latest research on NL2SQL, the use of pre-trained models as feature extractors for natural language and table schema has led to a very significant improvement in the effectiveness of the models. However, the current models do not take into account the degradation of the noisy labels on the overall SQL statement generation. It is crucial to reduce the impact of noisy labels on the overall SQL generation task and to maximize the return of accurate answers. To address this issue, we propose a restrictive constraint-based approach to mitigate the impact of noise-labeled labels on other tasks. In addition, parameter sharing approach is used in noiseless-labeled labels to capture each part’s correlations and improve the robustness of the model. In addition, we propose to use Kullback-Leibler divergence to constrain the discrepancy between hard and soft constrained coding of noisy labels. Our model is compared with some recent state-of-the-art methods, and experimental results show a significant improvement over the approach in this paper.

The steam turbine is one of the major pieces of equipment in thermal power plants. It is crucial to predict its output accurately. However, because of its complex coupling relationships with other equipment, it is still a challenging task. Previous methods mainly focus on the operation of the steam turbine individually while ignoring the coupling relationship with the condenser, which we believe is crucial for the prediction. Therefore, in this paper, to explore the coupling relationship between steam turbine and condenser, we propose a novel approach for steam turbine power prediction based on the encode-decoder framework guided by the condenser vacuum degree (CVD-EDF). In specific, the historical information within condenser operation conditions data is encoded using a long-short term memory network. Moreover, a connection module consisting of an attention mechanism and a convolutional neural network is incorporated to capture the local and global information in the encoder. The steam turbine power is predicted based on all the information. In this way, the coupling relationship between the condenser and the steam turbine is fully explored. Abundant experiments are conducted on real data from the power plant. The experimental results show that our proposed CVD-EDF achieves great improvements over several competitive methods. our method improves by 32.2% and 37.0% in terms of RMSE and MAE by comparing the LSTM at one-minute intervals.

Relation detection in knowledge base question answering, aims to identify the path(s) of relations starting from the topic entity node that is linked to the answer node in knowledge graph. Such path might consist of multiple relations, which we call multi-hop. Moreover, for a single question, there may exist multiple relation paths to the correct answer, which we call multi-label. However, most of existing approaches only detect one single path to obtain the answer without considering other correct paths, which might affect the final performance. Therefore, in this paper, we propose a novel divide-and-conquer approach for multi-label multi-hop relation detection (DC-MLMH) by decomposing it into head relation detection and conditional relation path generation. In specific, a novel path sampling mechanism is proposed to generate diverse relation paths for the inference stage. A majority-vote policy is employed to detect final KB answer. Comprehensive experiments were conducted on the FreebaseQA benchmark dataset. Experimental results show that the proposed approach not only outperforms other competitive multi-label baselines, but also has superiority over some state-of-art KBQA methods.

No abstract