Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant representations to bridge domain gap. More recently, self-training has been gaining momentum in UDA. Originated from semi-supervised learning, self-training uses unlabeled data efficiently by training on pseudo-labels. However, as corroborated in this work, under distributional shift in UDA, the pseudo-labels can be unreliable in terms of their large discrepancy from the ground truth labels. Thereby, we propose Cycle Self-Training (CST), a principled self-training algorithm that enforces pseudo-labels to generalize across domains. In the forward step, CST generates target pseudo-labels with a source-trained classifier. In the reverse step, CST trains a target classifier using target pseudo-labels, and then updates the shared representations to make the target classifier perform well on the source data. We introduce the Tsallis entropy, a novel regularization to improve the quality of target pseudo-labels. On quadratic neural networks, we prove that CST recovers target ground truth, while both invariant feature learning and vanilla self-training fail. Empirical results indicate that CST significantly improves over prior state-of-the-arts in standard UDA benchmarks across visual recognition and sentiment analysis tasks.
The outbreak of the novel coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been continuously affecting human lives and communities around the world in many ways, from cities under lockdown to new social experiences. Although in most cases COVID-19 results in mild illness, it has drawn global attention due to the extremely contagious nature of SARS-CoV-2. Governments and healthcare professionals, along with people and society as a whole, have taken any measures to break the chain of transition and flatten the epidemic curve. In this study, we used multiple data sources, i.e., PubMed and ArXiv, and built several machine learning models to characterize the landscape of current COVID-19 research by identifying the latent topics and analyzing the temporal evolution of the extracted research themes, publications similarity, and sentiments, within the time-frame of January- May 2020. Our findings confirm the types of research available in PubMed and ArXiv differ significantly, with the former exhibiting greater diversity in terms of COVID-19 related issues and the latter focusing more on intelligent systems/tools to predict/diagnose COVID-19. The special attention of the research community to the high-risk groups and people with complications was also confirmed.
Domestic Violence (DV) is considered as big social issue and there exists a strong relationship between DV and health impacts of the public. Existing research studies have focused on social media to track and analyse real world events like emerging trends, natural disasters, user sentiment analysis, political opinions, and health care. However there is less attention given on social welfare issues like DV and its impact on public health. Recently, the victims of DV turned to social media platforms to express their feelings in the form of posts and seek the social and emotional support, for sympathetic encouragement, to show compassion and empathy among public. But, it is difficult to mine the actionable knowledge from large conversational datasets from social media due to the characteristics of high dimensions, short, noisy, huge volume, high velocity, and so on. Hence, this paper will propose a novel framework to model and discover the various themes related to DV from the public domain. The proposed framework would possibly provide unprecedentedly valuable information to the public health researchers, national family health organizations, government and public with data enrichment and consolidation to improve the social welfare of the community. Thus provides actionable knowledge by monitoring and analysing continuous and rich user generated content.
Online reviews enable consumers to engage with companies and provide important feedback. Due to the complexity of the high-dimensional text, these reviews are often simplified as a single numerical score, e.g., ratings or sentiment scores. This work empirically examines the causal effects of user-generated online reviews on a granular level: we consider multiple aspects, e.g., the Food and Service of a restaurant. Understanding consumers' opinions toward different aspects can help evaluate business performance in detail and strategize business operations effectively. Specifically, we aim to answer interventional questions such as What will the restaurant popularity be if the quality w.r.t. its aspect Service is increased by 10%? The defining challenge of causal inference with observational data is the presence of "confounder", which might not be observed or measured, e.g., consumers' preference to food type, rendering the estimated effects biased and high-variance. To address this challenge, we have recourse to the multi-modal proxies such as the consumer profile information and interactions between consumers and businesses. We show how to effectively leverage the rich information to identify and estimate causal effects of multiple aspects embedded in online reviews. Empirical evaluations on synthetic and real-world data corroborate the efficacy and shed light on the actionable insight of the proposed approach.
Deep neural networks have a wide range of applications in solving various real-world tasks and have achieved satisfactory results, in domains such as computer vision, image classification, and natural language processing. Meanwhile, the security and robustness of neural networks have become imperative, as diverse researches have shown the vulnerable aspects of neural networks. Case in point, in Natural language processing tasks, the neural network may be fooled by an attentively modified text, which has a high similarity to the original one. As per previous research, most of the studies are focused on the image domain; Different from image adversarial attacks, the text is represented in a discrete sequence, traditional image attack methods are not applicable in the NLP field. In this paper, we propose a word-level NLP sentiment classifier attack model, which includes a self-attention mechanism-based word selection method and a greedy search algorithm for word substitution. We experiment with our attack model by attacking GRU and 1D-CNN victim models on IMDB datasets. Experimental results demonstrate that our model achieves a higher attack success rate and more efficient than previous methods due to the efficient word selection algorithms are employed and minimized the word substitute number. Also, our model is transferable, which can be used in the image domain with several modifications.
Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in higher-level spoken language understanding tasks, including using end-to-end models, but there are fewer annotated datasets for such tasks. At the same time, recent work shows the possibility of pre-training generic representations and then fine-tuning for several tasks using relatively little labeled data. We propose to create a suite of benchmark tasks for Spoken Language Understanding Evaluation (SLUE) consisting of limited-size labeled training sets and corresponding evaluation sets. This resource would allow the research community to track progress, evaluate pre-trained representations for higher-level tasks, and study open questions such as the utility of pipeline versus end-to-end approaches. We present the first phase of the SLUE benchmark suite, consisting of named entity recognition, sentiment analysis, and ASR on the corresponding datasets. We focus on naturally produced (not read or synthesized) speech, and freely available datasets. We provide new transcriptions and annotations on subsets of the VoxCeleb and VoxPopuli datasets, evaluation metrics and results for baseline models, and an open-source toolkit to reproduce the baselines and evaluate new models.
Extracting aspect-polarity pairs from texts is an important task of fine-grained sentiment analysis. While the existing approaches to this task have gained many progresses, they are limited at capturing relationships among aspect-polarity pairs in a text, thus degrading the extraction performance. Moreover, the existing state-of-the-art approaches, namely token-based se-quence tagging and span-based classification, have their own defects such as polarity inconsistency resulted from separately tagging tokens in the former and the heterogeneous categorization in the latter where aspect-related and polarity-related labels are mixed. In order to remedy the above defects, in-spiring from the recent advancements in relation extraction, we propose to generate aspect-polarity pairs directly from a text with relation extraction technology, regarding aspect-pairs as unary relations where aspects are enti-ties and the corresponding polarities are relations. Based on the perspective, we present a position- and aspect-aware sequence2sequence model for joint extraction of aspect-polarity pairs. The model is characterized with its ability to capture not only relationships among aspect-polarity pairs in a text through the sequence decoding, but also correlations between an aspect and its polarity through the position- and aspect-aware attentions. The experi-ments performed on three benchmark datasets demonstrate that our model outperforms the existing state-of-the-art approaches, making significant im-provement over them.
Various robustness evaluation methodologies from different perspectives have been proposed for different natural language processing (NLP) tasks. These methods have often focused on either universal or task-specific generalization capabilities. In this work, we propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) that incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint enables practitioners to automatically evaluate their models from all aspects or to customize their evaluations as desired with just a few lines of code. To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one. TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness. To validate TextFlint's utility, we performed large-scale empirical evaluations (over 67,000 evaluations) on state-of-the-art deep learning models, classic supervised methods, and real-world systems. Almost all models showed significant performance degradation, including a decline of more than 50% of BERT's prediction accuracy on tasks such as aspect-level sentiment classification, named entity recognition, and natural language inference. Therefore, we call for the robustness to be included in the model evaluation, so as to promote the healthy development of NLP technology.