Sentence semantic matching(SSM)is a fundamental research in solving natural language processing tasks such as question answering and machine translation.The latest SSM research benefits from deep learning techniques b...Sentence semantic matching(SSM)is a fundamental research in solving natural language processing tasks such as question answering and machine translation.The latest SSM research benefits from deep learning techniques by incorporating attention mechanism to semantically match given sentences.However,how to fully capture the semantic context without losing significant features for sentence encoding is still a challenge.To address this challenge,we propose a deep feature fusion model and integrate it into the most popular deep learning architecture for sentence matching task.The integrated architecture mainly consists of embedding layer,deep feature fusion layer,matching layer and prediction layer.In addition,we also compare the commonly used loss function,and propose a novel hybrid loss function integrating MSE and cross entropy together,considering confidence interval and threshold setting to preserve the indistinguishable instances in training process.To evaluate our model performance,we experiment on two real world public data sets:LCQMC and Quora.The experiment results demonstrate that our model outperforms the most existing advanced deep learning models for sentence matching,benefited from our enhanced loss function and deep feature fusion model for capturing semantic context.展开更多
基金supported by National Nature Science Foundation of China under Grant No.61502259National Key R&D Program of China under Grant No.2018YFC0831704Natural Science Foundation of Shandong Province under Grant No.ZR2017MF056.
文摘Sentence semantic matching(SSM)is a fundamental research in solving natural language processing tasks such as question answering and machine translation.The latest SSM research benefits from deep learning techniques by incorporating attention mechanism to semantically match given sentences.However,how to fully capture the semantic context without losing significant features for sentence encoding is still a challenge.To address this challenge,we propose a deep feature fusion model and integrate it into the most popular deep learning architecture for sentence matching task.The integrated architecture mainly consists of embedding layer,deep feature fusion layer,matching layer and prediction layer.In addition,we also compare the commonly used loss function,and propose a novel hybrid loss function integrating MSE and cross entropy together,considering confidence interval and threshold setting to preserve the indistinguishable instances in training process.To evaluate our model performance,we experiment on two real world public data sets:LCQMC and Quora.The experiment results demonstrate that our model outperforms the most existing advanced deep learning models for sentence matching,benefited from our enhanced loss function and deep feature fusion model for capturing semantic context.
