Current app ranking and recommendation systems are mainly based on user-generated information, e.g., number of downloads and ratings. However, new apps often have few (or even no) user feedback, suffering from the classic cold-start problem. How to q
uickly identify and then recommend new apps of high quality is a challenging issue. Here, a fundamental requirement is the capability to accurately measure an apps quality based on its inborn features, rather than user-generated features. Since users obtain first-hand experience of an app by interacting with its views, we speculate that the inborn features are largely related to the visual quality of individual views in an app and the ways the views switch to one another. In this work, we propose AppQ, a novel app quality grading and recommendation system that extracts inborn features of apps based on app source code. In particular, AppQ works in parallel to perform code analysis to extract app-level features as well as dynamic analysis to capture view-level layout hierarchy and the switching among views. Each app is then expressed as an attributed view graph, which is converted into a vector and fed to classifiers for recognizing its quality classes. Our evaluation with an app dataset from Google Play reports that AppQ achieves the best performance with accuracy of 85.0%. This shows a lot of promise to warm-start app grading and recommendation systems with AppQ.
Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speakers voice. Most previous CSST approaches rely on expensive high-quality data carrying desired speak
ing style during training and require a reference utterance to obtain speaking style descriptors as conditioning on the generation of a new sentence. This work presents Referee, a robust reference-free CSST approach for expressive TTS, which fully leverages low-quality data to learn speaking styles from text. Referee is built by cascading a text-to-style (T2S) model with a style-to-wave (S2W) model. Phonetic PosteriorGram (PPG), phoneme-level pitch and energy contours are adopted as fine-grained speaking style descriptors, which are predicted from text using the T2S model. A novel pretrain-refinement method is adopted to learn a robust T2S model by only using readily accessible low-quality data. The S2W model is trained with high-quality target data, which is adopted to effectively aggregate style descriptors and generate high-fidelity speech in the target speakers voice. Experimental results are presented, showing that Referee outperforms a global-style-token (GST)-based baseline approach in CSST.
The Graph Convolutional Networks (GCNs) proposed by Kipf and Welling are effective models for semi-supervised learning, but facing the obstacle of over-smoothing, which will weaken the representation ability of GCNs. Recently some works are proposed
to tackle with above limitation by randomly perturbing graph topology or feature matrix to generate data augmentations as input for training. However, these operations have to pay the price of information structure integrity breaking, and inevitably sacrifice information stochastically from original graph. In this paper, we introduce a novel graph entropy definition as an quantitative index to evaluate feature information diffusion among a graph. Under considerations of preserving graph entropy, we propose an effective strategy to generate perturbed training data using a stochastic mechanism but guaranteeing graph topology integrity and with only a small amount of graph entropy decaying. Extensive experiments have been conducted on real-world datasets and the results verify the effectiveness of our proposed method in improving semi-supervised node classification accuracy compared with a surge of baselines. Beyond that, our proposed approach significantly enhances the robustness and generalization ability of GCNs during the training process.
Singing voice conversion (SVC) is one promising technique which can enrich the way of human-computer interaction by endowing a computer the ability to produce high-fidelity and expressive singing voice. In this paper, we propose DiffSVC, an SVC syste
m based on denoising diffusion probabilistic model. DiffSVC uses phonetic posteriorgrams (PPGs) as content features. A denoising module is trained in DiffSVC, which takes destroyed mel spectrogram produced by the diffusion/forward process and its corresponding step information as input to predict the added Gaussian noise. We use PPGs, fundamental frequency features and loudness features as auxiliary input to assist the denoising process. Experiments show that DiffSVC can achieve superior conversion performance in terms of naturalness and voice similarity to current state-of-the-art SVC approaches.
Query focused summarization (QFS) models aim to generate summaries from source documents that can answer the given query. Most previous work on QFS only considers the query relevance criterion when producing the summary. However, studying the effect
of answer relevance in the summary generating process is also important. In this paper, we propose QFS-BART, a model that incorporates the explicit answer relevance of the source documents given the query via a question answering model, to generate coherent and answer-related summaries. Furthermore, our model can take advantage of large pre-trained models which improve the summarization performance significantly. Empirical results on the Debatepedia dataset show that the proposed model achieves the new state-of-the-art performance.
Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without computational c
ost increasing both at training and inference time. Besides, MoE based Transformer is a dynamic network which can adapt to the varying complexity of input instances in realworld applications. In this work, we explore the MoE based model for speech recognition, named SpeechMoE. To further control the sparsity of router activation and improve the diversity of gate values, we propose a sparsity L1 loss and a mean importance loss respectively. In addition, a new router architecture is used in SpeechMoE which can simultaneously utilize the information from a shared embedding network and the hierarchical representation of different MoE layers. Experimental results show that SpeechMoE can achieve lower character error rate (CER) with comparable computation cost than traditional static networks, providing 7.0%-23.0% relative CER improvements on four evaluation datasets.
Substantial efforts have been devoted to the investigation of spatiotemporal correlations for improving traffic speed prediction accuracy. However, existing works typically model the correlations based solely on the observed traffic state (e.g. traff
ic speed) without due consideration that different correlation measurements of the traffic data could exhibit a diverse set of patterns under different traffic situations. In addition, the existing works assume that all road segments can employ the same sampling frequency of traffic states, which is impractical. In this paper, we propose new measurements to model the spatial correlations among traffic data and show that the resulting correlation patterns vary significantly under various traffic situations. We propose a Heterogeneous Spatial Correlation (HSC) model to capture the spatial correlation based on a specific measurement, where the traffic data of varying road segments can be heterogeneous (i.e. obtained with different sampling frequency). We propose a Multi-fold Correlation Attention Network (MCAN), which relies on the HSC model to explore multi-fold spatial correlations and leverage LSTM networks to capture multi-fold temporal correlations to provide discriminating features in order to achieve accurate traffic prediction. The learned multi-fold spatiotemporal correlations together with contextual factors are fused with attention mechanism to make the final predictions. Experiments on real-world datasets demonstrate that the proposed MCAN model outperforms the state-of-the-art baselines.
Lay summarization aims to generate lay summaries of scientific papers automatically. It is an essential task that can increase the relevance of science for all of society. In this paper, we build a lay summary generation system based on the BART mode
l. We leverage sentence labels as extra supervision signals to improve the performance of lay summarization. In the CL-LaySumm 2020 shared task, our model achieves 46.00% Rouge1-F1 score.
Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs. It is a more challenging yet under-explored task compared to conventional single-hop
QG, where the questions are generated from the sentence containing the answer or nearby sentences in the same paragraph without complex reasoning. To address the additional challenges in multi-hop QG, we propose Multi-Hop Encoding Fusion Network for Question Generation (MulQG), which does context encoding in multiple hops with Graph Convolutional Network and encoding fusion via an Encoder Reasoning Gate. To the best of our knowledge, we are the first to tackle the challenge of multi-hop reasoning over paragraphs without any sentence-level information. Empirical results on HotpotQA dataset demonstrate the effectiveness of our method, in comparison with baselines on automatic evaluation metrics. Moreover, from the human evaluation, our proposed model is able to generate fluent questions with high completeness and outperforms the strongest baseline by 20.8% in the multi-hop evaluation. The code is publicly available at https://github.com/HLTCHKUST/MulQG}{https://github.com/HLTCHKUST/MulQG .
