We propose a method based on neural networks to identify the sentiment polarity of opinion words expressed on a specific aspect of a sentence. Although a large majority of works typically focus on leveraging the expressive power of neural networks in handling this task, we explore the possibility of integrating dependency trees with neural networks for representation learning. To this end, we present a convolution over a dependency tree (CDT) model which exploits a Bi-directional Long Short Term Memory (Bi-LSTM) to learn representations for features of a sentence, and further enhance the embeddings with a graph convolutional network (GCN) which operates directly on the dependency tree of the sentence. Our approach propagates both contextual and dependency information from opinion words to aspect words, offering discriminative properties for supervision. Experimental results ranks our approach as the new stateof-the-art in aspect-based sentiment classification.

Aspect-level sentiment classification (ALSC) aims at predicting the sentiment polarity of a specific aspect term occurring in a sentence. This task requires learning a representation by aggregating the relevant contextual features concerning the aspect term. Existing methods cannot sufficiently leverage the syntactic structure of the sentence, and hence are difficult to distinguish different sentiments for multiple aspects in a sentence. We perceive the limitations of the previous methods and propose a hypothesis about finding crucial contextual information with the help of syntactic structure. For this purpose, we present a neural network model named RepWalk which performs a replicated random walk on a syntax graph, to effectively focus on the informative contextual words. Empirical studies show that our model outperforms recent models on most of the benchmark datasets for the ALSC task. The results suggest that our method for incorporating syntactic structure enriches the representation for the classification.

A large majority of approaches have been proposed to leverage the dependency tree in the relation classification task. Recent works have focused on pruning irrelevant information from the dependency tree. The state-of-the-art Attention Guided Graph Convolutional Networks (AGGCNs) transforms the dependency tree into a weighted-graph to distinguish the relevance of nodes and edges for relation classification. However, in their approach, the graph is fully connected, which destroys the structure information of the original dependency tree. How to effectively make use of relevant information while ignoring irrelevant information from the dependency trees remains a challenge in the relation classification task. In this work, we learn to transform the dependency tree into a weighted graph by considering the syntax dependencies of the connected nodes and persisting the structure of the original dependency tree. We refer to this graph as a syntax-transport graph. We further propose a learnable syntax-transport attention graph convolutional network (LST-AGCN) which operates on the syntax-transport graph directly to distill the final representation which is sufficient for classification. Experiments on Semeval-2010 Task 8 and Tacred show our approach outperforms previous methods.

Unsupervised sentence representation learning is a fundamental problem in natural language processing. Recently, contrastive learning has made great success on this task. Existing constrastive learning based models usually apply random sampling to select negative examples for training. Previous work in computer vision has shown that hard negative examples help contrastive learning to achieve faster convergency and better optimization for representation learning. However, the importance of hard negatives in contrastive learning for sentence representation is yet to be explored. In this study, we prove that hard negatives are essential for maintaining strong gradient signals in the training process while random sampling negative examples is ineffective for sentence representation. Accordingly, we present a contrastive model, MixCSE, that extends the current state-of-the-art SimCSE by continually constructing hard negatives via mixing both positive and negative features. The superior performance of the proposed approach is demonstrated via empirical studies on Semantic Textual Similarity datasets and Transfer task datasets.

The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task. Existing methods using multi-task learning techniques to address the problem learn interactions among the two tasks through a shared network, where the shared information is passed into the taskspecific networks for prediction. However, such an approach hinders the model from learning explicit interactions between the two tasks to improve the performance on the individual tasks. As a solution, we design a multitask learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. Empirical studies on two real-world datasets confirm the superiority of the proposed model.

No abstract

No abstract

User interests modeling has been exploited as a critical component to improve the predictive performance of recommender systems. However, with the absence of explicit information to model user interests, most approaches to recommender systems exploit users activities (user generated contents or user ratings) to inference the interest of users. In reality, the relationship among users also serves as a rich source of information of shared interest. To this end, we propose a framework which avoids the sole dependence of user activities to infer user interests and allows the exploitation of the direct relationship between users to propagate user interests to improve system's performance. In this paper, we advocate a novel modeling framework. We construct a probabilistic user interests model and propose a user interests propagation algorithm (UIP), which applies a factor graph based approach to estimate the distribution of the interests of users. Moreover, we incorporate our UIP algorithm with conventional matrix factorization (MF) for recommender systems. Experimental results demonstrate that our proposed approach outperforms previous methods used for recommender systems.