Zhiyang Teng

Bio: Zhiyang Teng is an academic researcher from Westlake University. The author has contributed to research in topics: Computer science & Sentiment analysis. The author has an hindex of 12, co-authored 28 publications receiving 515 citations. Previous affiliations of Zhiyang Teng include Singapore University of Technology and Design & Chinese Academy of Sciences.

Context-Sensitive Lexicon Features for Neural Sentiment Analysis

Abstract: Sentiment lexicons have been leveraged as a useful source of features for sentiment analysis models, leading to the state-of-the-art accuracies. On the other hand, most existing methods use sentiment lexicons without considering context, typically taking the count, sum of strength, or maximum sentiment scores over the whole input. We propose a context-sensitive lexicon-based method based on a simple weighted-sum model, using a recurrent neural network to learn the sentiments strength, intensification and negation of lexicon sentiments in composing the sentiment value of sentences. Results show that our model can not only learn such operation details, but also give significant improvements over state-of-the-art recurrent neural network baselines without lexical features, achieving the best results on a Twitter benchmark.

Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning

Abstract: We focus on graph-to-sequence learning, which can be framed as transducing graph structures to sequences for text generation. To capture structural information associated with graphs, we investigat...

DeepClue: Visual Interpretation of Text-Based Deep Stock Prediction

Abstract: The recent advance of deep learning has enabled trading algorithms to predict stock price movements more accurately. Unfortunately, there is a significant gap in the real-world deployment of this breakthrough. For example, professional traders in their long-term careers have accumulated numerous trading rules, the myth of which they can understand quite well. On the other hand, deep learning models have been hardly interpretable. This paper presents DeepClue, a system built to bridge text-based deep learning models and end users through visually interpreting the key factors learned in the stock price prediction model. We make three contributions in DeepClue. First, by designing the deep neural network architecture for interpretation and applying an algorithm to extract relevant predictive factors, we provide a useful case on what can be interpreted out of the prediction model for end users. Second, by exploring hierarchies over the extracted factors and displaying these factors in an interactive, hierarchical visualization interface, we shed light on how to effectively communicate the interpreted model to end users. Specially, the interpretation separates the predictables from the unpredictables for stock prediction through the use of intercept model parameters and a risk visualization design. Third, we evaluate the integrated visualization system through two case studies in predicting the stock price with financial news and company-related tweets from social media. Quantitative experiments comparing the proposed neural network architecture with state-of-the-art models and the human baseline are conducted and reported. Feedbacks from an informal user study with domain experts are summarized and discussed in details. The study results demonstrate the effectiveness of DeepClue in helping to complete stock market investment and analysis tasks.

Inducing Target-Specific Latent Structures for Aspect Sentiment Classification

Abstract: 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.

Combining Discrete and Neural Features for Sequence Labeling

Abstract: Neural network models have recently received heated research attention in the natural language processing community. Compared with traditional models with discrete features, neural models have two main advantages. First, they take low-dimensional, real-valued embedding vectors as inputs, which can be trained over large raw data, thereby addressing the issue of feature sparsity in discrete models. Second, deep neural networks can be used to automatically combine input features, and including non-local features that capture semantic patterns that cannot be expressed using discrete indicator features. As a result, neural network models have achieved competitive accuracies compared with the best discrete models for a range of NLP tasks.

Deep learning for sentiment analysis: A survey

Abstract: Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state-of-the-art prediction results. Along with the success of deep learning in many other application domains, deep learning is also popularly used in sentiment analysis in recent years. This paper first gives an overview of deep learning and then provides a comprehensive survey of its current applications in sentiment analysis.

DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding

Abstract: Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, "Directional Self-Attention Network (DiSAN)", is then proposed to learn sentence embedding, based solely on the proposed attention without any RNN/CNN structure. DiSAN is only composed of a directional self-attention with temporal order encoded, followed by a multi-dimensional attention that compresses the sequence into a vector representation. Despite its simple form, DiSAN outperforms complicated RNN models on both prediction quality and time efficiency. It achieves the best test accuracy among all sentence encoding methods and improves the most recent best result by 1.02% on the Stanford Natural Language Inference (SNLI) dataset, and shows state-of-the-art test accuracy on the Stanford Sentiment Treebank (SST), Multi-Genre natural language inference (MultiNLI), Sentences Involving Compositional Knowledge (SICK), Customer Review, MPQA, TREC question-type classification and Subjectivity (SUBJ) datasets.

Sentiment Analysis: Mining Opinions, Sentiments, and Emotions

Abstract: Sentiment analysis is the computational study of people's opinions, sentiments, emotions, moods, and attitudes. This fascinating problem offers numerous research challenges, but promises insight useful to anyone interested in opinion analysis and social media analysis. This comprehensive introduction to the topic takes a natural-language-processing point of view to help readers understand the underlying structure of the problem and the language constructs commonly used to express opinions, sentiments, and emotions. The book covers core areas of sentiment analysis and also includes related topics such as debate analysis, intention mining, and fake-opinion detection. It will be a valuable resource for researchers and practitioners in natural language processing, computer science, management sciences, and the social sciences.In addition to traditional computational methods, this second edition includes recent deep learning methods to analyze and summarize sentiments and opinions, and also new material on emotion and mood analysis techniques, emotion-enhanced dialogues, and multimodal emotion analysis.