Lifelong Machine Learning (or Lifelong Learning) is an advanced machine learning paradigm that learns continuously, accumulates the knowledge learned in previous tasks, and uses it to help future learning. In the process, the learner becomes more and more knowledgeable and effective at learning. This learning ability is one of the hallmarks of human intelligence. However, the current dominant machine learning paradigm learns in isolation: given a training dataset, it runs a machine learning algorithm on the dataset to produce a model. It makes no attempt to retain the learned knowledge and use it in future learning. Although this isolated learning paradigm has been very successful, it requires a large number of training examples, and is only suitable for well-defined and narrow tasks. In comparison, we humans can learn effectively with a few examples because we have accumulated so much knowledge in the past which enables us to learn with little data or effort. Lifelong learning aims to achieve this capability. As statistical machine learning matures, it is time to make a major effort to break the isolated learning tradition and to study lifelong learning to bring machine learning to new heights. Applications such as intelligent assistants, chatbots, and physical robots that interact with humans and systems in real-life environments are also calling for such lifelong learning capabilities. Without the ability to accumulate the learned knowledge and use it to learn more knowledge incrementally, a system will probably never be truly intelligent. This book serves as an introductory text and survey to lifelong learning.

Lifelong Machine Learning

Cadmium (Cd) is one of the main pollutants in paddy fields, and its accumulation in rice (Oryza sativa L.) and subsequent transfer to food chain is a global environmental issue. This paper reviews the toxic effects, tolerance mechanisms, and management of Cd in a rice paddy. Cadmium toxicity decreases seed germination, growth, mineral nutrients, photosynthesis, and grain yield. It also causes oxidative stress and genotoxicity in rice. Plant response to Cd toxicity varies with cultivars, growth condition, and duration of Cd exposure. Under Cd stress, stimulation of antioxidant defense system, osmoregulation, ion homeostasis, and over production of signaling molecules are important tolerance mechanisms in rice. Several strategies have been proposed for the management of Cd-contaminated paddy soils. One such approach is the exogenous application of hormones, osmolytes, and signaling molecules. Moreover, Cd uptake and toxicity in rice can be decreased by proper application of essential nutrients such as nitrogen, zinc, iron, and selenium in Cd-contaminated soils. In addition, several inorganic (liming and silicon) and organic (compost and biochar) amendments have been applied in the soils to reduce Cd stress in rice. Selection of low Cd-accumulating rice cultivars, crop rotation, water management, and exogenous application of microbes could be a reasonable approach to alleviate Cd toxicity in rice. To draw a sound conclusion, long-term field trials are still required, including risks and benefit analysis for various management strategies.

Cadmium stress in rice: toxic effects, tolerance mechanisms, and management: a critical review.

Most machine-learning methods focus on classifying instances whose classes have already been seen in training. In practice, many applications require classifying instances whose classes have not been seen previously. Zero-shot learning is a powerful and promising learning paradigm, in which the classes covered by training instances and the classes we aim to classify are disjoint. In this paper, we provide a comprehensive survey of zero-shot learning. First of all, we provide an overview of zero-shot learning. According to the data utilized in model optimization, we classify zero-shot learning into three learning settings. Second, we describe different semantic spaces adopted in existing zero-shot learning works. Third, we categorize existing zero-shot learning methods and introduce representative methods under each category. Fourth, we discuss different applications of zero-shot learning. Finally, we highlight promising future research directions of zero-shot learning.

A Survey of Zero-Shot Learning: Settings, Methods, and Applications

大規模要約資源としてのNew York Times Annotated Corpus

The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.

Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review

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.

Deep learning for sentiment analysis: A survey

Deep Learning for Sentiment Analysis : A Survey

Aspect sentiment classification (ASC) is a fundamental task in sentiment analysis. Given an aspect/target and a sentence, the task classifies the sentiment polarity expressed on the target in the sentence. Memory networks (MNs) have been used for this task recently and have achieved state-of-the-art results. In MNs, attention mechanism plays a crucial role in detecting the sentiment context for the given target. However, we found an important problem with the current MNs in performing the ASC task. Simply improving the attention mechanism will not solve it. The problem is referred to as target-sensitive sentiment, which means that the sentiment polarity of the (detected) context is dependent on the given target and it cannot be inferred from the context alone. To tackle this problem, we propose the target-sensitive memory networks (TMNs). Several alternative techniques are designed for the implementation of TMNs and their effectiveness is experimentally evaluated.

/pdf/target-sensitive-memory-networks-for-aspect-sentiment-40fa4ddk61.pdf

Target-Sensitive Memory Networks for Aspect Sentiment Classification

Aspect-level sentiment analysis or opinion mining consists of several core sub-tasks: aspect extraction, opinion identification, polarity classification, and separation of general and aspect-specific opinions. Various topic models have been proposed by researchers to address some of these sub-tasks. However, there is little work on modeling all of them together. In this paper, we first propose a holistic fine-grained topic model, called the JAST (Joint Aspect-based Sentiment Topic) model, that can simultaneously model all of above problems under a unified framework. To further improve it, we incorporate the idea of lifelong machine learning and propose a more advanced model, called the LAST (Lifelong Aspect-based Sentiment Topic) model. LAST automatically mines the prior knowledge of aspect, opinion, and their correspondence from other products or domains. Such knowledge is automatically extracted and incorporated into the proposed LAST model without any human involvement. Our experiments using reviews of a large number of product domains show major improvements of the proposed models over state-of-the-art baselines.

Mining Aspect-Specific Opinion using a Holistic Lifelong Topic Model

Online reviews play a crucial role in helping consumers evaluate and compare products and services. This critical importance of reviews also incentivizes fraudsters (or spammers) to write fake or spam reviews to secretly promote or demote some target products and services. Existing approaches to detecting spam reviews and reviewers employed review contents, reviewer behaviors, star rating patterns, and reviewer-product networks for detection. In this research, we further discovered that reviewers' posting rates (number of reviews written in a period of time) also follow an interesting distribution pattern, which has not been reported before. That is, their posting rates are bimodal. Multiple spammers also tend to collectively and actively post reviews to the same set of products within a short time frame, which we call co-bursting. Furthermore, we found some other interesting patterns in individual reviewers' temporal dynamics and their co-bursting behaviors with other reviewers. Inspired by these findings, we first propose a two-mode Labeled Hidden Markov Model to model spamming using only individual reviewers' review posting times. We then extend it to the Coupled Hidden Markov Model to capture both reviewer posting behaviors and co-bursting signals. Our experiments show that the proposed model significantly outperforms state-of-the-art baselines in identifying individual spammers. Furthermore, we propose a co-bursting network based on co-bursting relations, which helps detect groups of spammers more effectively than existing approaches.

https://dl.acm.org/doi/pdf/10.1145/3038912.3052582

Shuai Wang

Papers

Deep learning for sentiment analysis: A survey

Deep Learning for Sentiment Analysis : A Survey

Target-Sensitive Memory Networks for Aspect Sentiment Classification

Mining Aspect-Specific Opinion using a Holistic Lifelong Topic Model

Bimodal Distribution and Co-Bursting in Review Spam Detection