Search for: All records

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 called ReviewRC based on a popular benchmark for aspect-based sentiment analysis. Since ReviewRC has limited training examples for RRC (and also for aspect-based sentiment analysis), we then explore a novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC. To show the generality of the approach, the proposed post-training is also applied to some other review-based tasks such as aspect extraction and aspect sentiment classification in aspect-based sentiment analysis. Experimental results demonstrate that the proposed post-training is highly effective. 

Classic supervised learning makes the closed-world assumption that the classes seen in testing must have appeared in training. However, this assumption is often violated in real-world applications. For example, in a social media site, new topics emerge constantly and in e-commerce, new categories of products appear daily. A model that cannot detect new/unseen topics or products is hard to function well in such open environments. A desirable model working in such environments must be able to (1) reject examples from unseen classes (not appeared in training) and (2) incrementally learn the new/unseen classes to expand the existing model. This is called open-world learning (OWL). This paper proposes a new OWL method based on meta-learning. The key novelty is that the model maintains only a dynamic set of seen classes that allows new classes to be added or deleted with no need for model re-training. Each class is represented by a small set of training examples. In testing, the meta-classifier only uses the examples of the maintained seen classes (including the newly added classes) on-the-fly for classification and rejection. Experimental results with e-commerce product classification show that the proposed method is highly effective. 

Abstract The ability to tailor a new crystalline structure and associated functionalities with a variety of stimuli is one of the key issues in material design. Developing synthetic routes to functional materials with partially absorbed nonmetallic elements (i.e., hydrogen and nitrogen) can open up more possibilities for preparing novel families of electronically active oxide compounds. Fast and reversible uptake and release of hydrogen in epitaxial ABO₃manganite films through an adapted low‐frequency inductively coupled plasma technology is introduced. Compared with traditional dopants of metallic cations, the plasma‐assisted hydrogen implantations not only produce reversibly structural transformations from pristine perovskite (PV) phase to a newly found protonation‐driven brownmillerite one but also regulate remarkably different electronic properties driving the material from a ferromagnetic metal to a weakly ferromagnetic insulator for a range of manganite (La_1−xSr_xMnO₃) thin films. Moreover, a reversible perovskite‐brownmillerite‐perovskite transition is achieved at a relatively low temperature (T≤ 350 °C), enabling multifunctional modulations for integrated electronic systems. The fast, low‐temperature control of structural and electronic properties by the facile hydrogenation/dehydrogenation treatment substantially widens the space for exploring new possibilities of novel properties in proton‐based multifunctional materials.