In this work, we propose a non-autoregressive seq2seq model that converts text to spectrogram. It is fully convolutional and obtains about 17.5 times speed-up over Deep Voice 3 at synthesis while maintaining comparable speech quality using a WaveNet vocoder. Interestingly, it has even fewer attention errors than the autoregressive model on the challenging test sentences. Furthermore, we build the first fully parallel neural text-to-speech system by applying the inverse autoregressive flow~(IAF) as the parallel neural vocoder. Our system can synthesize speech from text through a single feed-forward pass. We also explore a novel approach to train the IAF from scratch as a generative model for raw waveform, which avoids the need for distillation from a separately trained WaveNet.
In recent years, with the development of deep learning technology, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication. The automatically generated text is becoming more and more fluent so researchers begin to consider more anthropomorphic text generation technology, that is the conditional text generation, including emotional text generation, personalized text generation, and so on. Conditional text generation (c-TextGen) has thus become a research hotspot. As a promising research field, we find that many efforts have been paid to researches of c-TextGen. Therefore, we aim to give a comprehensive review of the new research trends of c-TextGen. We first give a brief literature review of text generation technology, based on which we formalize the concept model of c-TextGen. We further make an investigation of several different c-TextGen techniques, and illustrate the advantages and disadvantages of commonly used neural network models. Finally, we discuss the open issues and promising research directions of c-TextGen.
Machine Reading Comprehension (MRC) reveals the ability to understand a given text passage and answer questions based on it. Existing research works in MRC rely heavily on large-size models and corpus to improve the performance evaluated by metrics such as Exact Match ($EM$) and $F_1$. However, such a paradigm lacks sufficient interpretation to model capability and can not efficiently train a model with a large corpus. In this paper, we argue that a deep understanding of model capabilities and data properties can help us feed a model with appropriate training data based on its learning status. Specifically, we design an MRC capability assessment framework that assesses model capabilities in an explainable and multi-dimensional manner. Based on it, we further uncover and disentangle the connections between various data properties and model performance. Finally, to verify the effectiveness of the proposed MRC capability assessment framework, we incorporate it into a curriculum learning pipeline and devise a Capability Boundary Breakthrough Curriculum (CBBC) strategy, which performs a model capability-based training to maximize the data value and improve training efficiency. Extensive experiments demonstrate that our approach significantly improves performance, achieving up to an 11.22% / 8.71% improvement of $EM$ / $F_1$ on MRC tasks.
Deep learning transformer models become important by training on text data based on self-attention mechanisms. This manuscript demonstrated a novel universal spam detection model using pre-trained Google's Bidirectional Encoder Representations from Transformers (BERT) base uncased models with four datasets by efficiently classifying ham or spam emails in real-time scenarios. Different methods for Enron, Spamassain, Lingspam, and Spamtext message classification datasets, were used to train models individually in which a single model was obtained with acceptable performance on four datasets. The Universal Spam Detection Model (USDM) was trained with four datasets and leveraged hyperparameters from each model. The combined model was finetuned with the same hyperparameters from these four models separately. When each model using its corresponding dataset, an F1-score is at and above 0.9 in individual models. An overall accuracy reached 97%, with an F1 score of 0.96. Research results and implications were discussed.
From both human translators (HT) and machine translation (MT) researchers' point of view, translation quality evaluation (TQE) is an essential task. Translation service providers (TSPs) have to deliver large volumes of translations which meet customer specifications with harsh constraints of required quality level in tight time-frames and costs. MT researchers strive to make their models better, which also requires reliable quality evaluation. While automatic machine translation evaluation (MTE) metrics and quality estimation (QE) tools are widely available and easy to access, existing automated tools are not good enough, and human assessment from professional translators (HAP) are often chosen as the golden standard \cite{han-etal-2021-TQA}. Human evaluations, however, are often accused of having low reliability and agreement. Is this caused by subjectivity or statistics is at play? How to avoid the entire text to be checked and be more efficient with TQE from cost and efficiency perspectives, and what is the optimal sample size of the translated text, so as to reliably estimate the translation quality of the entire material? This work carries out such motivated research to correctly estimate the confidence intervals \cite{Brown_etal2001Interval} depending on the sample size of the translated text, e.g. the amount of words or sentences, that needs to be processed on TQE workflow step for confident and reliable evaluation of overall translation quality. The methodology we applied for this work is from Bernoulli Statistical Distribution Modelling (BSDM) and Monte Carlo Sampling Analysis (MCSA).
In this paper, we propose a Multi-stage Vision-language Pre-training (MVP) framework to learn cross-modality representation via multi-level semantic alignment. We introduce concepts in both modalities to construct two-level semantic representations for language and vision. Based on the multi-level input, we train the cross-modality model in two stages, namely, uni-modal learning and cross-modal learning. The former stage enforces within-modality interactions to learn multi-level semantics for each single modality. The latter stage enforces interactions across modalities via both coarse-grain and fine-grain semantic alignment tasks. Image-text matching and masked language modeling are then used to further optimize the pre-training model. Our model generates the-state-of-the-art results on several vision and language tasks.
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions. Our method can be boiled down to two stages: 1) text guided pose generation and 2) visual appearance transferred image synthesis. In the first stage, our method infers a reasonable target human pose based on the text. In the second stage, our method synthesizes a realistic and appearance transferred person image according to the text in conjunction with the target pose. Our method extracts sufficient information from the text and establishes a mapping between the image space and the language space, making generating and editing images corresponding to the description possible. We conduct extensive experiments to reveal the effectiveness of our method, as well as using the VQA Perceptual Score as a metric for evaluating the method. It shows for the first time that we can automatically edit the person image from the natural language descriptions.
Next generation reservoir computing based on nonlinear vector autoregression (NVAR) is applied to emulate simple dynamical system models and compared to numerical integration schemes such as Euler and the $2^\text{nd}$ order Runge-Kutta. It is shown that the NVAR emulator can be interpreted as a data-driven method used to recover the numerical integration scheme that produced the data. It is also shown that the approach can be extended to produce high-order numerical schemes directly from data. The impacts of the presence of noise and temporal sparsity in the training set is further examined to gauge the potential use of this method for more realistic applications.
Emotion analysis has been attracting researchers' attention. Most previous works in the artificial intelligence field focus on recognizing emotion rather than mining the reason why emotions are not or wrongly recognized. Correlation among emotions contributes to the failure of emotion recognition. In this paper, we try to fill the gap between emotion recognition and emotion correlation mining through natural language text from web news. Correlation among emotions, expressed as the confusion and evolution of emotion, is primarily caused by human emotion cognitive bias. To mine emotion correlation from emotion recognition through text, three kinds of features and two deep neural network models are presented. The emotion confusion law is extracted through orthogonal basis. The emotion evolution law is evaluated from three perspectives, one-step shift, limited-step shifts, and shortest path transfer. The method is validated using three datasets-the titles, the bodies, and the comments of news articles, covering both objective and subjective texts in varying lengths (long and short). The experimental results show that, in subjective comments, emotions are easily mistaken as anger. Comments tend to arouse emotion circulations of love-anger and sadness-anger. In objective news, it is easy to recognize text emotion as love and cause fear-joy circulation. That means, journalists may try to attract attention using fear and joy words but arouse the emotion love instead; After news release, netizens generate emotional comments to express their intense emotions, i.e., anger, sadness, and love. These findings could provide insights for applications regarding affective interaction such as network public sentiment, social media communication, and human-computer interaction.
Watermarking is an important copyright protection technology which generally embeds the identity information into the carrier imperceptibly. Then the identity can be extracted to prove the copyright from the watermarked carrier even after suffering various attacks. Most of the existing watermarking technologies take the nature images as carriers. Different from the natural images, document images are not so rich in color and texture, and thus have less redundant information to carry watermarks. This paper proposes an end-to-end document image watermarking scheme using the deep neural network. Specifically, an encoder and a decoder are designed to embed and extract the watermark. A noise layer is added to simulate the various attacks that could be encountered in reality, such as the Cropout, Dropout, Gaussian blur, Gaussian noise, Resize, and JPEG Compression. A text-sensitive loss function is designed to limit the embedding modification on characters. An embedding strength adjustment strategy is proposed to improve the quality of watermarked image with little loss of extraction accuracy. Experimental results show that the proposed document image watermarking technology outperforms three state-of-the-arts in terms of the robustness and image quality.