Federal Aviation Administration(FAA) and NASA technical reports indicate that the misunderstanding in radiotelephony communications is a primary causal factor associated with operation errors, and a sizable proportion...Federal Aviation Administration(FAA) and NASA technical reports indicate that the misunderstanding in radiotelephony communications is a primary causal factor associated with operation errors, and a sizable proportion of operation errors lead to read-back errors. We introduce deep learning method to solve this problem and propose a new semantic checking model based on Long Short-Time Memory network(LSTM) for intelligent read-back error checking. A meanpooling layer is added to the traditional LSTM, so as to utilize the information obtained by all the hidden activation vectors, and also to improve the robustness of the semantic vector extracted by LSTM. A MultiLayer Perceptron(MLP) layer, which can maintain the information of different regions in the concatenated vectors obtained by the mean-pooling layer, is applied instead of traditional similarity function in the new model to express the semantic similarity of the read-back pairs quantitatively. The K-Nearest Neighbor(KNN) classifier is used to verify whether the read-back pairs are consistent in semantics according to the output of MLP layer. Extensive experiments are conducted and the results show that the proposed model is more effective and more robust than the traditional checking model to verify the semantic consistency of read-backs automatically.展开更多
During the flight of the aircraft,the pilot must repeat the instruction sent by the controller,and the controller must further confirm these read-backs,in this way to further ensure the safety of air transportation.Ho...During the flight of the aircraft,the pilot must repeat the instruction sent by the controller,and the controller must further confirm these read-backs,in this way to further ensure the safety of air transportation.However,fatigue,tension,negligence and other human factors may prevent the controller from realizing read-back errors in time,which is a huge hidden danger for the safety of civil aviation transportation.This paper proposes a novel strategy to implement fine-grained semantic verification of radiotelephony read-backs by introducing interaction layer and attention mechanism at the output of BiLSTM model.Compared with the traditional twochannel verification strategy,the interaction layer is added to obtain fine-grained semantic matching relation representation,rather than connecting the BiLSTM output vectors to obtain the overall semantic representation of the sentence.And by adding attention layer,the new strategy can capture the potential semantic relation between the read-backs and the instructions,which is applicable to non-standard diction and abbreviated read-backs in real radiotelephony communications.Extensive experiments are conducted and the results show that the proposed new strategy is more effective than the traditional method for read-backs checking,and the average test accuracy of the new strategy based on the Chinese ATC radiotelephony read-backs corpus can reach 93.03%.展开更多
基金supported by the National Natural Science Foundation of China(Nos.61502498,U1433120 and 61806208)the Fundamental Research Funds for the Central Universities,China(No.3122017001)
文摘Federal Aviation Administration(FAA) and NASA technical reports indicate that the misunderstanding in radiotelephony communications is a primary causal factor associated with operation errors, and a sizable proportion of operation errors lead to read-back errors. We introduce deep learning method to solve this problem and propose a new semantic checking model based on Long Short-Time Memory network(LSTM) for intelligent read-back error checking. A meanpooling layer is added to the traditional LSTM, so as to utilize the information obtained by all the hidden activation vectors, and also to improve the robustness of the semantic vector extracted by LSTM. A MultiLayer Perceptron(MLP) layer, which can maintain the information of different regions in the concatenated vectors obtained by the mean-pooling layer, is applied instead of traditional similarity function in the new model to express the semantic similarity of the read-back pairs quantitatively. The K-Nearest Neighbor(KNN) classifier is used to verify whether the read-back pairs are consistent in semantics according to the output of MLP layer. Extensive experiments are conducted and the results show that the proposed model is more effective and more robust than the traditional checking model to verify the semantic consistency of read-backs automatically.
基金supported by Tianjin Natural Science Foundation of China(“Research on the Key Issues of Situational Cognition and Intelligent Early-warning for Civil Aviation Radiotelephony Communication”)the Fundamental Research Funds for the Central Universities,China(No.3122019058)the Project Funds for Civil Aviation,China(No.H01420210285).
文摘During the flight of the aircraft,the pilot must repeat the instruction sent by the controller,and the controller must further confirm these read-backs,in this way to further ensure the safety of air transportation.However,fatigue,tension,negligence and other human factors may prevent the controller from realizing read-back errors in time,which is a huge hidden danger for the safety of civil aviation transportation.This paper proposes a novel strategy to implement fine-grained semantic verification of radiotelephony read-backs by introducing interaction layer and attention mechanism at the output of BiLSTM model.Compared with the traditional twochannel verification strategy,the interaction layer is added to obtain fine-grained semantic matching relation representation,rather than connecting the BiLSTM output vectors to obtain the overall semantic representation of the sentence.And by adding attention layer,the new strategy can capture the potential semantic relation between the read-backs and the instructions,which is applicable to non-standard diction and abbreviated read-backs in real radiotelephony communications.Extensive experiments are conducted and the results show that the proposed new strategy is more effective than the traditional method for read-backs checking,and the average test accuracy of the new strategy based on the Chinese ATC radiotelephony read-backs corpus can reach 93.03%.
