arXiv subjects

Yang Feng

Publications and source records attributed to Yang Feng.

At least 217 records · Page 12Linked to original sources

arXiv2020

Future-Guided Incremental Transformer for Simultaneous Translation

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two weaknesses: low training speed caused by the recalculation of hidden states and lack of future source information to guide training. For the low training speed, we propose an incremental Transformer with an average embedding layer (AEL) to accelerate the speed of calculation of the hidden states during training. For future-guided training, we propose a conventional Transformer as the teacher of the incremental Transformer, and try to invisibly embed some future information in the model through knowledge distillation. We conducted experiments on Chinese-English and German-English simultaneous translation tasks and compared with the wait-k policy to evaluate the proposed method. Our method can effectively increase the training speed by about 28 times on average at different k and implicitly embed some predictive abilities in the model, achieving better translation quality than wait-k baseline.

cs.CL↗

arXiv2020

A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking

Recent studies in dialogue state tracking (DST) leverage historical information to determine states which are generally represented as slot-value pairs. However, most of them have limitations to efficiently exploit relevant context due to the lack of a powerful mechanism for modeling interactions between the slot and the dialogue history. Besides, existing methods usually ignore the slot imbalance problem and treat all slots indiscriminately, which limits the learning of hard slots and eventually hurts overall performance. In this paper, we propose to enhance the DST through employing a contextual hierarchical attention network to not only discern relevant information at both word level and turn level but also learn contextual representations. We further propose an adaptive objective to alleviate the slot imbalance problem by dynamically adjust weights of different slots during training. Experimental results show that our approach reaches 52.68% and 58.55% joint accuracy on MultiWOZ 2.0 and MultiWOZ 2.1 datasets respectively and achieves new state-of-the-art performance with considerable improvements (+1.24% and +5.98%).

cs.CL↗

arXiv2020

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation

Neural machine translation (NMT) models usually suffer from catastrophic forgetting during continual training where the models tend to gradually forget previously learned knowledge and swing to fit the newly added data which may have a different distribution, e.g. a different domain. Although many methods have been proposed to solve this problem, we cannot get to know what causes this phenomenon yet. Under the background of domain adaptation, we investigate the cause of catastrophic forgetting from the perspectives of modules and parameters (neurons). The investigation on the modules of the NMT model shows that some modules have tight relation with the general-domain knowledge while some other modules are more essential in the domain adaptation. And the investigation on the parameters shows that some parameters are important for both the general-domain and in-domain translation and the great change of them during continual training brings about the performance decline in general-domain. We conduct experiments across different language pairs and domains to ensure the validity and reliability of our findings.

cs.CL↗

arXiv2020

Generating Diverse Translation from Model Distribution with Dropout

Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inference, the posterior model distribution can be approximated with a variational distribution, from which the final models for inference are sampled. We conducted experiments on Chinese-English and English-German translation tasks and the results shows that our method makes a better trade-off between diversity and accuracy.

cs.CL↗

arXiv2020

Token-level Adaptive Training for Neural Machine Translation

There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural Machine Translation (NMT). The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less low-frequency tokens compared with the golden token distribution. However, low-frequency tokens may carry critical semantic information that will affect the translation quality once they are neglected. In this paper, we explored target token-level adaptive objectives based on token frequencies to assign appropriate weights for each target token during training. We aimed that those meaningful but relatively low-frequency words could be assigned with larger weights in objectives to encourage the model to pay more attention to these tokens. Our method yields consistent improvements in translation quality on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens where we can get 1.68, 1.02, and 0.52 BLEU increases compared with baseline, respectively. Further analyses show that our method can also improve the lexical diversity of translation.

cs.CL↗

arXiv2020

Universal Model for Multi-Domain Medical Image Retrieval

Medical Image Retrieval (MIR) helps doctors quickly find similar patients' data, which can considerably aid the diagnosis process. MIR is becoming increasingly helpful due to the wide use of digital imaging modalities and the growth of the medical image repositories. However, the popularity of various digital imaging modalities in hospitals also poses several challenges to MIR. Usually, one image retrieval model is only trained to handle images from one modality or one source. When there are needs to retrieve medical images from several sources or domains, multiple retrieval models need to be maintained, which is cost ineffective. In this paper, we study an important but unexplored task: how to train one MIR model that is applicable to medical images from multiple domains? Simply fusing the training data from multiple domains cannot solve this problem because some domains become over-fit sooner when trained together using existing methods. Therefore, we propose to distill the knowledge in multiple specialist MIR models into a single multi-domain MIR model via universal embedding to solve this problem. Using skin disease, x-ray, and retina image datasets, we validate that our proposed universal model can effectively accomplish multi-domain MIR.

cs.CV↗

arXiv2020

DeepGini: Prioritizing Massive Tests to Enhance the Robustness of Deep Neural Networks

Deep neural networks (DNN) have been deployed in many software systems to assist in various classification tasks. In company with the fantastic effectiveness in classification, DNNs could also exhibit incorrect behaviors and result in accidents and losses. Therefore, testing techniques that can detect incorrect DNN behaviors and improve DNN quality are extremely necessary and critical. However, the testing oracle, which defines the correct output for a given input, is often not available in the automated testing. To obtain the oracle information, the testing tasks of DNN-based systems usually require expensive human efforts to label the testing data, which significantly slows down the process of quality assurance. To mitigate this problem, we propose DeepGini, a test prioritization technique designed based on a statistical perspective of DNN. Such a statistical perspective allows us to reduce the problem of measuring misclassification probability to the problem of measuring set impurity, which allows us to quickly identify possibly-misclassified tests. To evaluate, we conduct an extensive empirical study on popular datasets and prevalent DNN models. The experimental results demonstrate that DeepGini outperforms existing coverage-based techniques in prioritizing tests regarding both effectiveness and efficiency. Meanwhile, we observe that the tests prioritized at the front by DeepGini are more effective in improving the DNN quality in comparison with the coverage-based techniques.

cs.SE↗

arXiv2020

CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation

Emotion-controllable response generation is an attractive and valuable task that aims to make open-domain conversations more empathetic and engaging. Existing methods mainly enhance the emotion expression by adding regularization terms to standard cross-entropy loss and thus influence the training process. However, due to the lack of further consideration of content consistency, the common problem of response generation tasks, safe response, is intensified. Besides, query emotions that can help model the relationship between query and response are simply ignored in previous models, which would further hurt the coherence. To alleviate these problems, we propose a novel framework named Curriculum Dual Learning (CDL) which extends the emotion-controllable response generation to a dual task to generate emotional responses and emotional queries alternatively. CDL utilizes two rewards focusing on emotion and content to improve the duality. Additionally, it applies curriculum learning to gradually generate high-quality responses based on the difficulties of expressing various emotions. Experimental results show that CDL significantly outperforms the baselines in terms of coherence, diversity, and relation to emotion factors.

cs.CL↗

arXiv2020

Nested Model Averaging on Solution Path for High-dimensional Linear Regression

We study the nested model averaging method on the solution path for a high-dimensional linear regression problem. In particular, we propose to combine model averaging with regularized estimators (e.g., lasso and SLOPE) on the solution path for high-dimensional linear regression. In simulation studies, we first conduct a systematic investigation on the impact of predictor ordering on the behavior of nested model averaging, then show that nested model averaging with lasso and SLOPE compares favorably with other competing methods, including the infeasible lasso and SLOPE with the tuning parameter optimally selected. A real data analysis on predicting the per capita violent crime in the United States shows an outstanding performance of the nested model averaging with lasso.

stat.ME↗

arXiv2020

Towards Multimodal Response Generation with Exemplar Augmentation and Curriculum Optimization

Recently, variational auto-encoder (VAE) based approaches have made impressive progress on improving the diversity of generated responses. However, these methods usually suffer the cost of decreased relevance accompanied by diversity improvements. In this paper, we propose a novel multimodal response generation framework with exemplar augmentation and curriculum optimization to enhance relevance and diversity of generated responses. First, unlike existing VAE-based models that usually approximate a simple Gaussian posterior distribution, we present a Gaussian mixture posterior distribution (i.e, multimodal) to further boost response diversity, which helps capture complex semantics of responses. Then, to ensure that relevance does not decrease while diversity increases, we fully exploit similar examples (exemplars) retrieved from the training data into posterior distribution modeling to augment response relevance. Furthermore, to facilitate the convergence of Gaussian mixture prior and posterior distributions, we devise a curriculum optimization strategy to progressively train the model under multiple training criteria from easy to hard. Experimental results on widely used SwitchBoard and DailyDialog datasets demonstrate that our model achieves significant improvements compared to strong baselines in terms of diversity and relevance.

cs.CL↗

arXiv2020

Video-based Person Re-Identification using Gated Convolutional Recurrent Neural Networks

Deep neural networks have been successfully applied to solving the video-based person re-identification problem with impressive results reported. The existing networks for person re-id are designed to extract discriminative features that preserve the identity information. Usually, whole video frames are fed into the neural networks and all the regions in a frame are equally treated. This may be a suboptimal choice because many regions, e.g., background regions in the video, are not related to the person. Furthermore, the person of interest may be occluded by another person or something else. These unrelated regions may hinder person re-identification. In this paper, we introduce a novel gating mechanism to deep neural networks. Our gating mechanism will learn which regions are helpful for person re-identification and let these regions pass the gate. The unrelated background regions or occluding regions are filtered out by the gate. In each frame, the color channels and optical flow channels provide quite different information. To better leverage such information, we generate one gate using the color channels and another gate using the optical flow channels. These two gates are combined to provide a more reliable gate with a novel fusion method. Experimental results on two major datasets demonstrate the performance improvements due to the proposed gating mechanism.

cs.CV↗

arXiv2020

Unifying Specialist Image Embedding into Universal Image Embedding

Deep image embedding provides a way to measure the semantic similarity of two images. It plays a central role in many applications such as image search, face verification, and zero-shot learning. It is desirable to have a universal deep embedding model applicable to various domains of images. However, existing methods mainly rely on training specialist embedding models each of which is applicable to images from a single domain. In this paper, we study an important but unexplored task: how to train a single universal image embedding model to match the performance of several specialists on each specialist's domain. Simply fusing the training data from multiple domains cannot solve this problem because some domains become overfitted sooner when trained together using existing methods. Therefore, we propose to distill the knowledge in multiple specialists into a universal embedding to solve this problem. In contrast to existing embedding distillation methods that distill the absolute distances between images, we transform the absolute distances between images into a probabilistic distribution and minimize the KL-divergence between the distributions of the specialists and the universal embedding. Using several public datasets, we validate that our proposed method accomplishes the goal of universal image embedding.

cs.CV↗

arXiv2020

Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog

Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multi-task learning method to learn joint representations among different modalities as well as generate informative and fluent responses. Our method extends the natural language generation pre-trained model to multimodal dialogue generation task. Our system achieves the best performance in both objective and subjective evaluations in the challenge.

cs.CL↗

arXiv2020

Neyman-Pearson classification: parametrics and sample size requirement

The Neyman-Pearson (NP) paradigm in binary classification seeks classifiers that achieve a minimal type II error while enforcing the prioritized type I error controlled under some user-specified level $α$. This paradigm serves naturally in applications such as severe disease diagnosis and spam detection, where people have clear priorities among the two error types. Recently, Tong, Feng and Li (2018) proposed a nonparametric umbrella algorithm that adapts all scoring-type classification methods (e.g., logistic regression, support vector machines, random forest) to respect the given type I error upper bound $α$ with high probability, without specific distributional assumptions on the features and the responses. Universal the umbrella algorithm is, it demands an explicit minimum sample size requirement on class $0$, which is often the more scarce class, such as in rare disease diagnosis applications. In this work, we employ the parametric linear discriminant analysis (LDA) model and propose a new parametric thresholding algorithm, which does not need the minimum sample size requirements on class $0$ observations and thus is suitable for small sample applications such as rare disease diagnosis. Leveraging both the existing nonparametric and the newly proposed parametric thresholding rules, we propose four LDA-based NP classifiers, for both low- and high-dimensional settings. On the theoretical front, we prove NP oracle inequalities for one proposed classifier, where the rate for excess type II error benefits from the explicit parametric model assumption. Furthermore, as NP classifiers involve a sample splitting step of class $0$ observations, we construct a new adaptive sample splitting scheme that can be applied universally to NP classifiers, and this adaptive strategy reduces the type II error of these classifiers.

stat.ME↗

arXiv2019

Modeling Fluency and Faithfulness for Diverse Neural Machine Translation

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution. However, the strategy casts all the portion of the distribution to the ground truth word and ignores other words in the target vocabulary even when the ground truth word cannot dominate the distribution. To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. The evaluation module accesses each prediction from the perspectives of fluency and faithfulness to encourage the model to generate the word which has a fluent connection with its past and future translation and meanwhile tends to form a translation equivalent in meaning to the source. The experiments on multiple translation tasks show that our method can achieve significant improvements over strong baselines.

cs.CL↗

arXiv2019

Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation

Non-Autoregressive Neural Machine Translation (NAT) achieves significant decoding speedup through generating target words independently and simultaneously. However, in the context of non-autoregressive translation, the word-level cross-entropy loss cannot model the target-side sequential dependency properly, leading to its weak correlation with the translation quality. As a result, NAT tends to generate influent translations with over-translation and under-translation errors. In this paper, we propose to train NAT to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The bag-of-ngrams training objective is differentiable and can be efficiently calculated, which encourages NAT to capture the target-side sequential dependency and correlates well with the translation quality. We validate our approach on three translation tasks and show that our approach largely outperforms the NAT baseline by about 5.0 BLEU scores on WMT14 En$\leftrightarrow$De and about 2.5 BLEU scores on WMT16 En$\leftrightarrow$Ro.

cs.CL↗

arXiv2019

Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation

Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a representation via hierarchical attention networks. However, this method neither considers the relationship between context words nor distinguishes the roles of context words. To address this problem, we propose a query-guided capsule networks to cluster context information into different perspectives from which the target translation may concern. Experiment results show that our method can significantly outperform strong baselines on multiple data sets of different domains.

cs.CL↗

arXiv2019

Unveiling Elite Developers' Activities in Open Source Projects

Open-source developers, particularly the elite developers, maintain a diverse portfolio of contributing activities. They do not only commit source code but also spend a significant amount of effort on other communicative, organizational, and supportive activities. However, almost all prior research focuses on a limited number of specific activities and fails to analyze elite developers' activities in a comprehensive way. To bridge this gap, we conduct an empirical study with fine-grained event data from 20 large open-source projects hosted on GitHub. Thus, we investigate elite developers' contributing activities and their impacts on project outcomes. Our analyses reveal three key findings: (1) they participate in a variety of activities while technical contributions (e.g., coding) accounting for a small proportion only; (2) they tend to put more effort into supportive and communicative activities and less effort into coding as the project grows; (3) their participation in non-technical activities is negatively associated with the project's outcomes in term of productivity and software quality. These results provide a panoramic view of elite developers' activities and can inform an individual's decision making about effort allocation, thus leading to finer project outcomes. The results also provide implications for supporting these elite developers.

cs.SE↗