arXiv subjects

Yu Wu

Publications and source records attributed to Yu Wu.

At least 253 records · Page 14Linked to original sources

arXiv2020

Semantic Mask for Transformer based End-to-End Speech Recognition

Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the mapping from the input sequence to the output sequence from scratch, without the assumption of prior knowledge such as the alignments. However, this model is prone to overfitting, especially when the amount of training data is limited. Inspired by SpecAugment and BERT, in this paper, we propose a semantic mask based regularization for training such kind of end-to-end (E2E) model. The idea is to mask the input features corresponding to a particular output token, e.g., a word or a word-piece, in order to encourage the model to fill the token based on the contextual information. While this approach is applicable to the encoder-decoder framework with any type of neural network architecture, we study the transformer-based model for ASR in this work. We perform experiments on Librispeech 960h and TedLium2 data sets, and achieve the state-of-the-art performance on the test set in the scope of E2E models.

cs.CL↗

arXiv2020

Symbiotic Attention with Privileged Information for Egocentric Action Recognition

Egocentric video recognition is a natural testbed for diverse interaction reasoning. Due to the large action vocabulary in egocentric video datasets, recent studies usually utilize a two-branch structure for action recognition, ie, one branch for verb classification and the other branch for noun classification. However, correlation studies between the verb and the noun branches have been largely ignored. Besides, the two branches fail to exploit local features due to the absence of a position-aware attention mechanism. In this paper, we propose a novel Symbiotic Attention framework leveraging Privileged information (SAP) for egocentric video recognition. Finer position-aware object detection features can facilitate the understanding of actor's interaction with the object. We introduce these features in action recognition and regard them as privileged information. Our framework enables mutual communication among the verb branch, the noun branch, and the privileged information. This communication process not only injects local details into global features but also exploits implicit guidance about the spatio-temporal position of an on-going action. We introduce novel symbiotic attention (SA) to enable effective communication. It first normalizes the detection guided features on one branch to underline the action-relevant information from the other branch. SA adaptively enhances the interactions among the three sources. To further catalyze this communication, spatial relations are uncovered for the selection of most action-relevant information. It identifies the most valuable and discriminative feature for classification. We validate the effectiveness of our SAP quantitatively and qualitatively. Notably, it achieves the state-of-the-art on two large-scale egocentric video datasets.

cs.CV↗

arXiv2019

Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation

End-to-end speech translation, a hot topic in recent years, aims to translate a segment of audio into a specific language with an end-to-end model. Conventional approaches employ multi-task learning and pre-training methods for this task, but they suffer from the huge gap between pre-training and fine-tuning. To address these issues, we propose a Tandem Connectionist Encoding Network (TCEN) which bridges the gap by reusing all subnets in fine-tuning, keeping the roles of subnets consistent, and pre-training the attention module. Furthermore, we propose two simple but effective methods to guarantee the speech encoder outputs and the MT encoder inputs are consistent in terms of semantic representation and sequence length. Experimental results show that our model outperforms baselines 2.2 BLEU on a large benchmark dataset.

cs.CL↗

arXiv2019

Unsupervised Context Rewriting for Open Domain Conversation

Context modeling has a pivotal role in open domain conversation. Existing works either use heuristic methods or jointly learn context modeling and response generation with an encoder-decoder framework. This paper proposes an explicit context rewriting method, which rewrites the last utterance by considering context history. We leverage pseudo-parallel data and elaborate a context rewriting network, which is built upon the CopyNet with the reinforcement learning method. The rewritten utterance is beneficial to candidate retrieval, explainable context modeling, as well as enabling to employ a single-turn framework to the multi-turn scenario. The empirical results show that our model outperforms baselines in terms of the rewriting quality, the multi-turn response generation, and the end-to-end retrieval-based chatbots.

cs.CL↗

arXiv2019

Explicit Cross-lingual Pre-training for Unsupervised Machine Translation

Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is inexplicit and limited. In this paper, we propose a novel cross-lingual pre-training method for unsupervised machine translation by incorporating explicit cross-lingual training signals. Specifically, we first calculate cross-lingual n-gram embeddings and infer an n-gram translation table from them. With those n-gram translation pairs, we propose a new pre-training model called Cross-lingual Masked Language Model (CMLM), which randomly chooses source n-grams in the input text stream and predicts their translation candidates at each time step. Experiments show that our method can incorporate beneficial cross-lingual information into pre-trained models. Taking pre-trained CMLM models as the encoder and decoder, we significantly improve the performance of unsupervised machine translation.

cs.CL↗

arXiv2019

Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification

Prevailing deep convolutional neural networks (CNNs) for person re-IDentification (reID) are usually built upon ResNet or VGG backbones, which were originally designed for classification. Because reID is different from classification, the architecture should be modified accordingly. We propose to automatically search for a CNN architecture that is specifically suitable for the reID task. There are three aspects to be tackled. First, body structural information plays an important role in reID but it is not encoded in backbones. Second, Neural Architecture Search (NAS) automates the process of architecture design without human effort, but no existing NAS methods incorporate the structure information of input images. Third, reID is essentially a retrieval task but current NAS algorithms are merely designed for classification. To solve these problems, we propose a retrieval-based search algorithm over a specifically designed reID search space, named Auto-ReID. Our Auto-ReID enables the automated approach to find an efficient and effective CNN architecture for reID. Extensive experiments demonstrate that the searched architecture achieves state-of-the-art performance while reducing 50% parameters and 53% FLOPs compared to others.

cs.CV↗

arXiv2019

Cascaded Revision Network for Novel Object Captioning

Image captioning, a challenging task where the machine automatically describes an image by sentences, has drawn significant attention in recent years. Despite the remarkable improvements of recent approaches, however, these methods are built upon a large set of training image-sentence pairs. The expensive labor efforts hence limit the captioning model to describe the wider world. In this paper, we present a novel network structure, Cascaded Revision Network, which aims at relieving the problem by equipping the model with out-of-domain knowledge. CRN first tries its best to describe an image using the existing vocabulary from in-domain knowledge. Due to the lack of out-of-domain knowledge, the caption may be inaccurate or include ambiguous words for the image with unknown (novel) objects. We propose to re-edit the primary captioning sentence by a series of cascaded operations. We introduce a perplexity predictor to find out which words are most likely to be inaccurate given the input image. Thereafter, we utilize external knowledge from a pre-trained object detection model and select more accurate words from detection results by the visual matching module. In the last step, we design a semantic matching module to ensure that the novel object is fit in the right position. By this novel cascaded captioning-revising mechanism, CRN can accurately describe images with unseen objects. We validate the proposed method with state-of-the-art performance on the held-out MSCOCO dataset as well as scale to ImageNet, demonstrating the effectiveness of this method.

cs.MM↗

arXiv2019

Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019

In this report, we present the Baidu-UTS submission to the EPIC-Kitchens Action Recognition Challenge in CVPR 2019. This is the winning solution to this challenge. In this task, the goal is to predict verbs, nouns, and actions from the vocabulary for each video segment. The EPIC-Kitchens dataset contains various small objects, intense motion blur, and occlusions. It is challenging to locate and recognize the object that an actor interacts with. To address these problems, we utilize object detection features to guide the training of 3D Convolutional Neural Networks (CNN), which can significantly improve the accuracy of noun prediction. Specifically, we introduce a Gated Feature Aggregator module to learn from the clip feature and the object feature. This module can strengthen the interaction between the two kinds of activations and avoid gradient exploding. Experimental results demonstrate our approach outperforms other methods on both seen and unseen test set.

cs.CV↗

arXiv2019

Improving Person Re-identification by Attribute and Identity Learning

Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into consideration. However, we find the attributes, containing detailed local descriptions, are beneficial in allowing the re-ID model to learn more discriminative feature representations. In this paper, based on the complementarity of attribute labels and ID labels, we propose an attribute-person recognition (APR) network, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes. We manually annotate attribute labels for two large-scale re-ID datasets, and systematically investigate how person re-ID and attribute recognition benefit from each other. In addition, we re-weight the attribute predictions considering the dependencies and correlations among the attributes. The experimental results on two large-scale re-ID benchmarks demonstrate that by learning a more discriminative representation, APR achieves competitive re-ID performance compared with the state-of-the-art methods. We use APR to speed up the retrieval process by ten times with a minor accuracy drop of 2.92% on Market-1501. Besides, we also apply APR on the attribute recognition task and demonstrate improvement over the baselines.

cs.CV↗

arXiv2019

Electrically Tunable Wafer-Sized Three-Dimensional Topological Insulator Thin Films Grown by Magnetron Sputtering

Three-dimensional (3D) topological insulators (TIs) are candidate materials for various electronic and spintronic devices due to their strong spin-orbit coupling and unique surface electronic structure. Rapid, low-cost preparation of large-area TI thin films compatible with conventional semiconductor technology is key to the practical applications of TIs. Here, we show that wafer-sized Bi2Te3 family TI and magnetic TI films with decent quality and well-controlled composition and properties can be prepared on amorphous SiO2/Si substrates by magnetron cosputtering. The SiO2/Si substrates enable us to electrically tune (Bi1-xSbx)2Te3 and Cr-doped (Bi1-xSbx)2Te3 TI films between p-type and n-type behavior and thus study the phenomena associated with topological surface states, such as the quantum anomalous Hall effect (QAHE). This work significantly facilitates the fabrication of TI-based devices for electronic and spintronic applications.

physics.app-ph↗

arXiv2018

Response Generation by Context-aware Prototype Editing

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm for response generation, that is response generation by editing, which significantly increases the diversity and informativeness of the generation results. Our assumption is that a plausible response can be generated by slightly revising an existing response prototype. The prototype is retrieved from a pre-defined index and provides a good start-point for generation because it is grammatical and informative. We design a response editing model, where an edit vector is formed by considering differences between a prototype context and a current context, and then the edit vector is fed to a decoder to revise the prototype response for the current context. Experiment results on a large scale dataset demonstrate that the response editing model outperforms generative and retrieval-based models on various aspects.

cs.CL↗

arXiv2018

Text Morphing

In this paper, we introduce a novel natural language generation task, termed as text morphing, which targets at generating the intermediate sentences that are fluency and smooth with the two input sentences. We propose the Morphing Networks consisting of the editing vector generation networks and the sentence editing networks which are trained jointly. Specifically, the editing vectors are generated with a recurrent neural networks model from the lexical gap between the source sentence and the target sentence. Then the sentence editing networks iteratively generate new sentences with the current editing vector and the sentence generated in the previous step. We conduct experiments with 10 million text morphing sequences which are extracted from the Yelp review dataset. Experiment results show that the proposed method outperforms baselines on the text morphing task. We also discuss directions and opportunities for future research of text morphing.

cs.CL↗

arXiv2018

Neural Melody Composition from Lyrics

In this paper, we study a novel task that learns to compose music from natural language. Given the lyrics as input, we propose a melody composition model that generates lyrics-conditional melody as well as the exact alignment between the generated melody and the given lyrics simultaneously. More specifically, we develop the melody composition model based on the sequence-to-sequence framework. It consists of two neural encoders to encode the current lyrics and the context melody respectively, and a hierarchical decoder to jointly produce musical notes and the corresponding alignment. Experimental results on lyrics-melody pairs of 18,451 pop songs demonstrate the effectiveness of our proposed methods. In addition, we apply a singing voice synthesizer software to synthesize the "singing" of the lyrics and melodies for human evaluation. Results indicate that our generated melodies are more melodious and tuneful compared with the baseline method.

cs.CL↗

arXiv2018

Keyphrase Generation with Correlation Constraints

In this paper, we study automatic keyphrase generation. Although conventional approaches to this task show promising results, they neglect correlation among keyphrases, resulting in duplication and coverage issues. To solve these problems, we propose a new sequence-to-sequence architecture for keyphrase generation named CorrRNN, which captures correlation among multiple keyphrases in two ways. First, we employ a coverage vector to indicate whether the word in the source document has been summarized by previous phrases to improve the coverage for keyphrases. Second, preceding phrases are taken into account to eliminate duplicate phrases and improve result coherence. Experiment results show that our model significantly outperforms the state-of-the-art method on benchmark datasets in terms of both accuracy and diversity.

cs.CL↗

arXiv2018

Decoupled Novel Object Captioner

Image captioning is a challenging task where the machine automatically describes an image by sentences or phrases. It often requires a large number of paired image-sentence annotations for training. However, a pre-trained captioning model can hardly be applied to a new domain in which some novel object categories exist, i.e., the objects and their description words are unseen during model training. To correctly caption the novel object, it requires professional human workers to annotate the images by sentences with the novel words. It is labor expensive and thus limits its usage in real-world applications. In this paper, we introduce the zero-shot novel object captioning task where the machine generates descriptions without extra sentences about the novel object. To tackle the challenging problem, we propose a Decoupled Novel Object Captioner (DNOC) framework that can fully decouple the language sequence model from the object descriptions. DNOC has two components. 1) A Sequence Model with the Placeholder (SM-P) generates a sentence containing placeholders. The placeholder represents an unseen novel object. Thus, the sequence model can be decoupled from the novel object descriptions. 2) A key-value object memory built upon the freely available detection model, contains the visual information and the corresponding word for each object. The SM-P will generate a query to retrieve the words from the object memory. The placeholder will then be filled with the correct word, resulting in a caption with novel object descriptions. The experimental results on the held-out MSCOCO dataset demonstrate the ability of DNOC in describing novel concepts in the zero-shot novel object captioning task.

cs.CV↗

arXiv2018

Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts

We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat. To imitate human behavior, we propose managing the flow of human-machine interactions with the dialogue acts as policies. The policies and response generation are jointly learned from human-human conversations, and the former is further optimized with a reinforcement learning approach. With the dialogue acts, we achieve significant improvement over state-of-the-art methods on response quality for given contexts and dialogue length in both machine-machine simulation and human-machine conversation.

cs.CL↗

arXiv2018

Application of compact TiO$_2$ layer fabricated by pulsed laser deposition in organometal trihalide perovskite solar cells

Organometal trihalide perovskite solar cells have been rapidly developed and attracted much attention in recent years due to their high photoelectric conversion efficiency and low cost. Pulsed laser deposition (PLD) is a widely adopted technology which is used in the preparation of thin films, especially oxide thin films. With this technology, the thickness and composition of films can be conveniently and accurately controlled. In the structure of perovskite solar cells, TiO$_2$ layer working as the n-type semiconductor is used to block holes and transport electrons into electrode, which is crucial for the performance of whole devices. We introduced the PLD technique into preparation of TiO$_2$ layer. In comparison with common spin coating method, TiO$_2$ layer prepared by this technique is ultrathin and more compact. Compact TiO$_2$ (c-TiO$_2$) layers with optimized thickness of 32 nm have been prepared by the PLD method and the highest efficiency of 13.95 % for the MAPbI$_3$-based solar cell devices has been achieved.

physics.app-ph↗

arXiv2018

Dictionary-Guided Editing Networks for Paraphrase Generation

An intuitive way for a human to write paraphrase sentences is to replace words or phrases in the original sentence with their corresponding synonyms and make necessary changes to ensure the new sentences are fluent and grammatically correct. We propose a novel approach to modeling the process with dictionary-guided editing networks which effectively conduct rewriting on the source sentence to generate paraphrase sentences. It jointly learns the selection of the appropriate word level and phrase level paraphrase pairs in the context of the original sentence from an off-the-shelf dictionary as well as the generation of fluent natural language sentences. Specifically, the system retrieves a set of word level and phrase level araphrased pairs derived from the Paraphrase Database (PPDB) for the original sentence, which is used to guide the decision of which the words might be deleted or inserted with the soft attention mechanism under the sequence-to-sequence framework. We conduct experiments on two benchmark datasets for paraphrase generation, namely the MSCOCO and Quora dataset. The evaluation results demonstrate that our dictionary-guided editing networks outperforms the baseline methods.

cs.CL↗