Tri-training for Dependency Parsing Domain Adaptation

In recent years, the research on dependency parsing focuses on improving the accuracy of the domain-specific (in-domain) test datasets and has made remarkable progress. However, there are innumerable scenarios in the real world that are not covered by the dataset, namely, the out-of-domain dataset. As a result, parsers that perform well on the in-domain data usually suffer from significant performance degradation on the out-of-domain data. Therefore, to adapt the existing in-domain parsers with high performance to a new domain scenario, cross-domain transfer learning methods are essential to solve the domain problem in parsing. This paper examines two scenarios for cross-domain transfer learning: semi-supervised and unsupervised cross-domain transfer learning. Specifically, we adopt a pre-trained language model BERT for training on the source domain (in-domain) data at the subword level and introduce self-training methods varied from tri-training for these two scenarios. The evaluation results on the NLPCC-2019 shared task and universal dependency parsing task indicate the effectiveness of the adopted approaches on cross-domain transfer learning and show the potential of self-learning to cross-lingual transfer learning.

An Intelligent Mechanism to Automatically Discover Emerging Technology Trends: Exploring Regulatory Technology

Technology trend analysis uses data relevant to historical performance and extrapolates it to estimate and assess the future potential of technology. Such analysis is used to analyze emerging technologies or predict the growing markets that influence the resulting social or economic development to assist in effective decision-making. Traditional trend analysis methods are time-consuming and require considerable labor. Moreover, the implemented processes may largely rely on the specific knowledge of the domain experts. With the advancement in the areas of science and technology, emerging cross-domain trends have received growing attention for its considerable influence on society and the economy. Consequently, emerging cross-domain predictions that combine or complement various technologies or integrate with diverse disciplines may be more critical than other tools and applications in the same domain. This study uses a design science research methodology, a text mining technique, and social network analysis (SNA) to analyze the development trends concerning the presentation of the product or service information on a company's website. This study applies regulatory technology (RegTech) as a case to analyze and justify the emerging cross-disciplinary trend. Furthermore, an experimental study is conducted using the Google search engine to verify and validate the proposed research mechanism at the end of this study. The study results reveal that, compared with Google Trends and Google Correlate, the research mechanism proposed in this study is more illustrative, feasible, and promising because it reduces noise and avoids the additional time and effort required to perform a further in-depth exploration to obtain the information.

Adversarial Cross-domain Community Question Retrieval

Community Q&A forum is a special type of social media that provides a platform to raise questions and to answer them (both by forum participants), to facilitate online information sharing. Currently, community Q&A forums in professional domains have attracted a large number of users by offering professional knowledge. To support information access and save users’ efforts of raising new questions, they usually come with a question retrieval function, which retrieves similar existing questions (and their answers) to a user’s query. However, it can be difficult for community Q&A forums to cover all domains, especially those emerging lately with little labeled data but great discrepancy from existing domains. We refer to this scenario as cross-domain question retrieval. To handle the unique challenges of cross-domain question retrieval, we design a model based on adversarial training, namely, X-QR , which consists of two modules—a domain discriminator and a sentence matcher. The domain discriminator aims at aligning the source and target data distributions and unifying the feature space by domain-adversarial training. With the assistance of the domain discriminator, the sentence matcher is able to learn domain-consistent knowledge for the final matching prediction. To the best of our knowledge, this work is among the first to investigate the domain adaption problem of sentence matching for community Q&A forums question retrieval. The experiment results suggest that the proposed X-QR model offers better performance than conventional sentence matching methods in accomplishing cross-domain community Q&A tasks.

Mixed Information Flow for Cross-Domain Sequential Recommendations

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains. Previous studies have investigated the flow of behavioral information by exploring the connection between items from different domains. The flow of knowledge (i.e., the connection between knowledge from different domains) has so far been neglected. In this article, we propose a mixed information flow network for cross-domain sequential recommendation to consider both the flow of behavioral information and the flow of knowledge by incorporating a behavior transfer unit and a knowledge transfer unit . The proposed mixed information flow network is able to decide when cross-domain information should be used and, if so, which cross-domain information should be used to enrich the sequence representation according to users’ current preferences. Extensive experiments conducted on four e-commerce datasets demonstrate that the proposed mixed information flow network is able to improve recommendation performance in different domains by modeling mixed information flow. In this article, we focus on the application of mixed information flow network s to a scenario with two domains, but the method can easily be extended to multiple domains.

A Transformer-Based Approach to Multilingual Fake News Detection in Low-Resource Languages

Fake news classification is one of the most interesting problems that has attracted huge attention to the researchers of artificial intelligence, natural language processing, and machine learning (ML). Most of the current works on fake news detection are in the English language, and hence this has limited its widespread usability, especially outside the English literate population. Although there has been a growth in multilingual web content, fake news classification in low-resource languages is still a challenge due to the non-availability of an annotated corpus and tools. This article proposes an effective neural model based on the multilingual Bidirectional Encoder Representations from Transformer (BERT) for domain-agnostic multilingual fake news classification. Large varieties of experiments, including language-specific and domain-specific settings, are conducted. The proposed model achieves high accuracy in domain-specific and domain-agnostic experiments, and it also outperforms the current state-of-the-art models. We perform experiments on zero-shot settings to assess the effectiveness of language-agnostic feature transfer across different languages, showing encouraging results. Cross-domain transfer experiments are also performed to assess language-independent feature transfer of the model. We also offer a multilingual multidomain fake news detection dataset of five languages and seven different domains that could be useful for the research and development in resource-scarce scenarios.

Cross-Domain Feature Similarity Guided Blind Image Quality Assessment

This work proposes an end-to-end cross-domain feature similarity guided deep neural network for perceptual quality assessment. Our proposed blind image quality assessment approach is based on the observation that features similarity across different domains (e.g., Semantic Recognition and Quality Prediction) is well correlated with the subjective quality annotations. Such phenomenon is validated by thoroughly analyze the intrinsic interaction between an object recognition task and a quality prediction task in terms of characteristics of the human visual system. Based on the observation, we designed an explicable and self-contained cross-domain feature similarity guided BIQA framework. Experimental results on both authentical and synthetic image quality databases demonstrate the superiority of our approach, as compared to the state-of-the-art models.

Multi-Source and Multi-Representation Adaptation for Cross-Domain Electroencephalography Emotion Recognition

Due to the non-invasiveness and high precision of electroencephalography (EEG), the combination of EEG and artificial intelligence (AI) is often used for emotion recognition. However, the internal differences in EEG data have become an obstacle to classification accuracy. To solve this problem, considering labeled data from similar nature but different domains, domain adaptation usually provides an attractive option. Most of the existing researches aggregate the EEG data from different subjects and sessions as a source domain, which ignores the assumption that the source has a certain marginal distribution. Moreover, existing methods often only align the representation distributions extracted from a single structure, and may only contain partial information. Therefore, we propose the multi-source and multi-representation adaptation (MSMRA) for cross-domain EEG emotion recognition, which divides the EEG data from different subjects and sessions into multiple domains and aligns the distribution of multiple representations extracted from a hybrid structure. Two datasets, i.e., SEED and SEED IV, are used to validate the proposed method in cross-session and cross-subject transfer scenarios, experimental results demonstrate the superior performance of our model to state-of-the-art models in most settings.

Sub- and Supra-Second Timing in Auditory Perception: Evidence for Cross-Domain Relationships

Previous studies indicate that there are at least two levels of temporal processing: the sub- and supra-second domains. The relationship between these domains remains unclear. The aim of this study was to test whether performance on the sub-second level is related to that on the supra-second one, or whether these two domains operate independently. Participants were 118 healthy adults (mean age = 23 years). The sub-second level was studied with a temporal-order judgment task and indexed by the Temporal Order Threshold (TOT), on which lower values corresponded to better performance. On the basis of TOT results, the initial sample was classified into two groups characterized by either higher temporal efficiency (HTE) or lower temporal efficiency (LTE). Next, the efficiency of performance on the supra-second level was studied in these two groups using the subjective accentuation task, in which participants listened to monotonous sequences of beats and were asked to mentally accentuate every n-th beat to create individual rhythmic patterns. The extent of temporal integration was assessed on the basis of the number of beats being united and better performance corresponded to longer units. The novel results are differences between groups in this temporal integration. The HTE group integrated beats in significantly longer units than did the LTE group. Moreover, for tasks with higher mental load, the HTE group relied more on a constant time strategy, whereas the LTE group relied more on mental counting, probably because of less efficient temporal integration. These findings provide insight into associations between sub- and supra-second levels of processing and point to a common time keeping system, which is active independently of temporal domain.