Dependency trees have been intensively used with graph neural networks for aspect-based sentiment classification.Though being effective, such methods rely on external dependency parsers, which can be unavailable for low-resource languages or perform worse in low-resource domains.In addition, dependency trees are also not optimized for aspect-based sentiment classification.In this paper, we propose an aspect-specific and language-agnostic discrete latent opinion tree model as an alternative structure to explicit dependency trees.To ease the learning of complicated structured latent variables, we build a connection between aspect-to-context attention scores and syntactic distances, inducing trees from the attention scores.Results on six English benchmarks, one Chinese dataset and one Korean dataset show that our model can achieve competitive performance and interpretability.

Deep latent variable models such as variational autoencoders and energy-based models are widely used for neural text generation. Most of them focus on matching the prior distribution with the posterior distribution of the latent variable for text reconstruction. In addition to instance-level reconstruction, this paper aims to integrate contrastive learning in the latent space, forcing the latent variables to learn high-level semantics by exploring inter-instance relationships. Experiments on various text generation benchmarks show the effectiveness of our proposed method. We also empirically show that our method can mitigate the posterior collapse issue for latent variable based text generation models.

Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment.Recently, graph convolutional networks based on linguistic dependency trees have been studied for this task.However, the dependency parsing accuracy of commercial product comments or tweets might be unsatisfactory.To tackle this problem, we associate linguistic dependency trees with automatically induced aspectspecific graphs.We propose gating mechanisms to dynamically combine information from word dependency graphs and latent graphs which are learned by self-attention networks.Our model can complement supervised syntactic features with latent semantic dependencies.Experimental results on five benchmarks show the effectiveness of our proposed latent models, giving significantly better results than models without using latent graphs.

Context-aware applications automatically adapt their behavior according to environmental conditions, also known as contexts. However, in practice contexts are often inaccurate, noisy or even inconsistent (e.g., two RFID readers may report different numbers for the same set of goods processed). These kinds of problematic contexts may cause context-aware applications to behave abnormally or even fail. It is thus desirable to detect and resolve context inconsistency. In this paper, we propose a hybrid approach to detect problematic contexts and resolve resulting context inconsistencies with the help of context-aware application semantics. By combining low-level context inconsistency resolution with high-level application error recovery, our approach can resolve the inconsistent contexts more effectively. Moreover, error recovery cost for context-aware applications is reduced. Our experimental results show that our approach outperforms existing approaches in terms of more accurate inconsistency resolution and less error recovery cost.