A Survey of Quantum-Cognitively Inspired Sentiment Analysis Models
Beijing Institute of Technology（北京理工大学）；University of Copenhagen（哥本哈根大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Zhengzhou University of Light Industry（郑州轻工业大学）；The Open University（开放大学）
Yaochen Liu, Qiuchi Li, Benyou Wang, Yazhou Zhang, Dawei Song
Quantum theory, originally proposed as a physical theory to describe the motions of microscopic particles, has been applied to various non-physics domains involving human cognition and decision-making that are inherently uncertain and exhibit certain non-classical, quantum-like characteristics. Sentiment analysis is a typical example of such domains. In the last few years, by leveraging the modeling power of quantum probability (a non-classical probability stemming from quantum mechanics methodology) and deep neural networks, a range of novel quantum-cognitively inspired models for sentiment analysis have emerged and performed well. This survey presents a timely overview of the latest developments in this fascinating cross-disciplinary area. We first provide a background of quantum probability and quantum cognition at a theoretical level, analyzing their advantages over classical theories in modeling the cognitive aspects of sentiment analysis. Then, recent quantum-cognitively inspired models are introduced and discussed in detail, focusing on how they approach the key challenges of the sentiment analysis task. Finally, we discuss the limitations of the current research and highlight future research directions.
The Open University（开放大学）；University of Padua（帕多瓦大学）；Queensland University of Technology（昆士兰科技大学）；Beijing Institute of Technology（北京理工大学）
Video sentiment analysis as a decision-making process is inherently complex, involving the fusion of decisions from multiple modalities and the so-caused cognitive biases. Inspired by recent advances in quantum cognition, we show that the sentiment judgment from one modality could be incompatible with the judgment from another, i.e., the order matters and they cannot be jointly measured to produce a final decision. Thus the cognitive process exhibits "quantum-like" biases that cannot be captured by classical probability theories. Accordingly, we propose a fundamentally new, quantum cognitively…
National Institute of Standards and Technology（美国国家标准与技术研究院）
When people try to understand nuanced language they typically process multiple input sensor modalities to complete this cognitive task. It turns out the human brain has even a specialized neuron formation, called sagittal stratum, to help us understand sarcasm. We use this biological formation as the inspiration for designing a neural network architecture that combines predictions of different models on the same text to construct robust, accurate and computationally efficient classifiers for sentiment analysis and study several different realizations. Among them, we propose a systematic new ap…
Shandong University（山东大学）；National University of Singapore（新加坡国立大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Existing studies on multimodal sentiment analysis heavily rely on textual modality and unavoidably induce the spurious correlations between textual words and sentiment labels. This greatly hinders the model generalization ability. To address this problem, we define the task of out-of-distribution (OOD) multimodal sentiment analysis. This task aims to estimate and mitigate the bad effect of textual modality for strong OOD generalization. To this end, we embrace causal inference, which inspects the causal relationships via a causal graph. From the graph, we find that the spurious correlations ar…
University of Stuttgart（斯图加特大学）；Universitat Pompeu Fabra（庞培法布拉大学）
Domain adaptation for sentiment analysis is challenging due to the fact that supervised classifiers are very sensitive to changes in domain. The two most prominent approaches to this problem are structural correspondence learning and autoencoders. However, they either require long training times or suffer greatly on highly divergent domains. Inspired by recent advances in cross-lingual sentiment analysis, we provide a novel perspective and cast the domain adaptation problem as an embedding projection task. Our model takes as input two mono-domain embedding spaces and learns to project them to …
Tsinghua University（清华大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Question-answering plays an important role in e-commerce as it allows potential customers to actively seek crucial information about products or services to help their purchase decision making. Inspired by the recent success of machine reading comprehension (MRC) on formal documents, this paper explores the potential of turning customer reviews into a large source of knowledge that can be exploited to answer user questions.~We call this problem Review Reading Comprehension (RRC). To the best of our knowledge, no existing work has been done on RRC. In this work, we first build an RRC dataset ca…
Sentiment analysis is attracting more and more attentions and has become a very hot research topic due to its potential applications in personalized recommendation, opinion mining, etc. Most of the existing methods are based on either textual or visual data and can not achieve satisfactory results, as it is very hard to extract sufficient information from only one single modality data. Inspired by the observation that there exists strong semantic correlation between visual and textual data in social medias, we propose an end-to-end deep fusion convolutional neural network to jointly learn text…
TwiSE at SemEval-2016 Task 4: Twitter Sentiment Classification
University of Grenoble-Alpes（格勒诺布尔-阿尔卑斯大学）
本文介绍了“TwiSE”团队参加SemEval 2016挑战赛的情况。具体来说，我们参与了任务4，即“Twitter中的情感分析”，为此我们为子任务A、B、C和D实现了情感分类系统。我们的方法包括两个步骤。在第一步中，我们受到之前版本此类挑战参与者工作的启发，生成并验证用于Twitter情感评估的多种功能集。在第二步中，我们专注于不同子任务的评估措施的优化。为此，我们通过验证任务组织者提供的数据来检查不同的学习策略。在我们的最终提交中，我们对子任务A使用了集成学习方法（堆叠泛化），对其余子任务使用了单一线性模型。在官方排行榜上，我们在子任务A、B、C和D中分别排名9/35、8/19、1/11和2/14。\footnote{We make the code available for research purposes at \url{https://github.com/balikasg/SemEval2016-Twitter\_Sentiment\_Evaluation}.}
Multimodal sentiment analysis and depression estimation are two important research topics that aim to predict human mental states using multimodal data. Previous research has focused on developing effective fusion strategies for exchanging and integrating mind-related information from different modalities. Some MLP-based techniques have recently achieved considerable success in a variety of computer vision tasks. Inspired by this, we explore multimodal approaches with a feature-mixing perspective in this study. To this end, we introduce CubeMLP, a multimodal feature processing framework based …
Current Explainable AI (ExAI) methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking of such methods and their wider adoption. In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the explainability of SA models from two angles. First, we evaluate the strength of the extracted "rationales" in faithfully explaining the predicted outcome. Second, we measure the agreement between ExAI m…
Center of Cognitive Science（认知科学中心）；Natural Language Learning Group（自然语言学习组）；Technische Universität Darmstadt（达姆施塔特工业大学）
Adversarial attacks expose important blind spots of deep learning systems. While word- and sentence-level attack scenarios mostly deal with finding semantic paraphrases of the input that fool NLP models, character-level attacks typically insert typos into the input stream. It is commonly thought that these are easier to defend via spelling correction modules. In this work, we show that both a standard spellchecker and the approach of Pruthi et al. (2019), which trains to defend against insertions, deletions and swaps, perform poorly on the character-level benchmark recently proposed in Eger an…
Estimating the intensity of emotion has gained significance as modern textual inputs in potential applications like social media, e-retail markets, psychology, advertisements etc., carry a lot of emotions, feelings, expressions along with its meaning. However, the approaches of traditional sentiment analysis primarily focuses on classifying the sentiment in general (positive or negative) or at an aspect level(very positive, low negative, etc.) and cannot exploit the intensity information. Moreover, automatically identifying emotions like anger, fear, joy, sadness, disgust etc., from text intro…
From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning
School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院）；Shanghai Qiji Zhifeng Co., Ltd.（上海启智丰科技有限公司）；Ocean University of China（中国海洋大学）
University of Padova（帕多瓦大学）；The Open University（开放大学）；Beijing Institute of Technology（北京理工大学）
A challenging task for word embeddings is to capture the emergent meaning or polarity of a combination of individual words. For example, existing approaches in word embeddings will assign high probabilities to the words "Penguin" and "Fly" if they frequently co-occur, but it fails to capture the fact that they occur in an opposite sense - Penguins do not fly. We hypothesize that humans do not associate a single polarity or sentiment to each word. The word contributes to the overall polarity of a combination of words depending upon which other words it is combined with. This is analogous to the…
