Multi-Channel CNN Based Inner-Attention for Compound Sentence Relation Classification

Abstract

Relation classification is a vital task in natural language processing, and it is screening for semantic relation between clauses in texts. This paper describes a study of relation classification on Chinese compound sentences without connectives. There exists an implicit relation in a compound sentence without connectives, which makes it difficult to realize the recognition of relation. The major challenges that relation classification modeling faces are how to obtain the contextual representation of sentence and relation dependence features between clauses. To solve this problem, we propose a novel Inatt-MCNN model to extract sentence features and classify relations by combining multi-channel CNN and Inner-attention mechanism. This network structure utilizes CNN to extract local features of sentences and Inner-attention to capture sentence-level feature representations for this relation classification task. Besides, since the Innerattention is based on Bi-LSTM, the global and long-term dependence semantic information can be well obtained in Inatt-MCNN to promote the model performance. We conduct experiments on two public Chinese discourse datasets: the Chinese compound sentence corpus (CCCS) dataset and the Tsinghua Chinese Treebank(TCT) dataset. Compared with the previous public methods, Inatt-MCNN model has superior performance and achieves the highest accuracy, especially on the CCCS dataset.INDEX TERMS Relation classification, multi-channel CNN, inner-attention mechanism, Chinese compound sentence without connectives.

Identification of RNA pseudouridine sites using deep learning approaches

“…Generally, in a CNN model, the inputs are connected to some convolution and max-pooling layers, followed by a couple of fully connected layers that are connected to the output layer. But in our case, the preprocessed inputs are fed to a multi-channel CNN model which has been very effective in various text classification tasks [ 27 , 28 ]. The motivation behind this approach was to make sure a sequence is processed at different lengths at a time.…”

Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM

“…CNNs are typical feedforward neural networks with convolutional computations and deep structures. CNNs, as some of the most representative deep learning models, have been widely applied in many fields, and numerous related applications, including image classification [ 24 , 25 , 26 , 27 , 28 ], natural language processing [ 29 , 30 ], face recognition [ 31 , 32 ], video analysis [ 33 , 34 ], and pedestrian detection [ 35 , 36 ].…”

Multi-Attention-Based Capsule Network for Uyghur Personal Pronouns Resolution

“…Following previous work [6], [8], [9], [18] on anaphora resolution, metrics employed to evaluate our model are: precision, recall, and F-score (F). We report the performance for each hyperparameter except as the overall result.…”

“…Anaphora resolution is an important sub-task in natural language processing. In recent years, deep learning models for anaphora resolution have been widely investigated [6]- [11]. These methods concentrate on anaphoric pronoun resolution, applying numerous neural network models to pronoun-candidate antecedent prediction.…”