arXiv subjects

Xiaodong He

Publications and source records attributed to Xiaodong He.

At least 109 records · Page 6Linked to original sources

arXiv2020

DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images

Diabetic retinopathy (DR) is a complication of diabetes that severely affects eyes. It can be graded into five levels of severity according to international protocol. However, optimizing a grading model to have strong generalizability requires a large amount of balanced training data, which is difficult to collect particularly for the high severity levels. Typical data augmentation methods, including random flipping and rotation, cannot generate data with high diversity. In this paper, we propose a diabetic retinopathy generative adversarial network (DR-GAN) to synthesize high-resolution fundus images which can be manipulated with arbitrary grading and lesion information. Thus, large-scale generated data can be used for more meaningful augmentation to train a DR grading and lesion segmentation model. The proposed retina generator is conditioned on the structural and lesion masks, as well as adaptive grading vectors sampled from the latent grading space, which can be adopted to control the synthesized grading severity. Moreover, a multi-scale spatial and channel attention module is devised to improve the generation ability to synthesize details. Multi-scale discriminators are designed to operate from large to small receptive fields, and joint adversarial losses are adopted to optimize the whole network in an end-to-end manner. With extensive experiments evaluated on the EyePACS dataset connected to Kaggle, as well as the FGADR dataset, we validate the effectiveness of our method, which can both synthesize highly realistic (1280 x 1280) controllable fundus images and contribute to the DR grading task.

eess.IV↗

arXiv2020

Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis

Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into natural and expressive speech. In this paper, we propose to use the text embeddings of the neighboring sentences to improve the prosody generation for each utterance of a paragraph in an end-to-end fashion without using any explicit prosody features. More specifically, cross-utterance (CU) context vectors, which are produced by an additional CU encoder based on the sentence embeddings extracted by a pre-trained BERT model, are used to augment the input of the Tacotron2 decoder. Two types of BERT embeddings are investigated, which leads to the use of different CU encoder structures. Experimental results on a Mandarin audiobook dataset and the LJ-Speech English audiobook dataset demonstrate the use of CU information can improve the naturalness and expressiveness of the synthesized speech. Subjective listening testing shows most of the participants prefer the voice generated using the CU encoder over that generated using standard Tacotron2. It is also found that the prosody can be controlled indirectly by changing the neighbouring sentences.

eess.AS↗

arXiv2020

Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training

This paper aims to enhance the few-shot relation classification especially for sentences that jointly describe multiple relations. Due to the fact that some relations usually keep high co-occurrence in the same context, previous few-shot relation classifiers struggle to distinguish them with few annotated instances. To alleviate the above relation confusion problem, we propose CTEG, a model equipped with two mechanisms to learn to decouple these easily-confused relations. On the one hand, an Entity-Guided Attention (EGA) mechanism, which leverages the syntactic relations and relative positions between each word and the specified entity pair, is introduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations by playing a pushing-away game between classifying a sentence into a true relation and its confusing relation. Extensive experiments are conducted on the FewRel dataset, and the results show that our proposed model achieves comparable and even much better results to strong baselines in terms of accuracy. Furthermore, the ablation test and case study verify the effectiveness of our proposed EGA and CAT, especially in addressing the relation confusion problem.

cs.CL↗

arXiv2020

The role of hydrophobic interactions in folding of $β$-sheets

Exploring the protein-folding problem has been a long-standing challenge in molecular biology. Protein folding is highly dependent on folding of secondary structures as the way to pave a native folding pathway. Here, we demonstrate that a feature of a large hydrophobic surface area covering most side-chains on one side or the other side of adjacent $β$-strands of a $β$-sheet is prevail in almost all experimentally determined $β$-sheets, indicating that folding of $β$-sheets is most likely triggered by multistage hydrophobic interactions among neighbored side-chains of unfolded polypeptides, enable $β$-sheets fold reproducibly following explicit physical folding codes in aqueous environments. $β$-turns often contain five types of residues characterized with relatively small exposed hydrophobic proportions of their side-chains, that is explained as these residues can block hydrophobic effect among neighbored side-chains in sequence. Temperature dependence of the folding of $β$-sheet is thus attributed to temperature dependence of the strength of the hydrophobicity. The hydrophobic-effect-based mechanism responsible for $β$-sheets folding is verified by bioinformatics analyses of thousands of results available from experiments. The folding codes in amino acid sequence that dictate formation of a $β$-hairpin can be deciphered through evaluating hydrophobic interaction among side-chains of an unfolded polypeptide from a $β$-strand-like thermodynamic metastable state.

q-bio.BM↗

arXiv2020

Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product

Product attribute values are essential in many e-commerce scenarios, such as customer service robots, product recommendations, and product retrieval. While in the real world, the attribute values of a product are usually incomplete and vary over time, which greatly hinders the practical applications. In this paper, we propose a multimodal method to jointly predict product attributes and extract values from textual product descriptions with the help of the product images. We argue that product attributes and values are highly correlated, e.g., it will be easier to extract the values on condition that the product attributes are given. Thus, we jointly model the attribute prediction and value extraction tasks from multiple aspects towards the interactions between attributes and values. Moreover, product images have distinct effects on our tasks for different product attributes and values. Thus, we selectively draw useful visual information from product images to enhance our model. We annotate a multimodal product attribute value dataset that contains 87,194 instances, and the experimental results on this dataset demonstrate that explicitly modeling the relationship between attributes and values facilitates our method to establish the correspondence between them, and selectively utilizing visual product information is necessary for the task. Our code and dataset will be released to the public.

cs.CL↗

arXiv2020

A hydrophobic-interaction-based mechanism trigger docking between the SARS CoV 2 spike and angiotensin-converting enzyme 2

A recent experimental study found that the binding affinity between the cellular receptor human angiotensin converting enzyme 2 (ACE2) and receptor-binding domain (RBD) in spike (S) protein of novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is more than 10-fold higher than that of the original severe acute respiratory syndrome coronavirus (SARS-CoV). However, main-chain structures of the SARS-CoV-2 RBD are almost the same with that of the SARS-CoV RBD. Understanding physical mechanism responsible for the outstanding affinity between the SARS-CoV-2 S and ACE2 is the "urgent challenge" for developing blockers, vaccines and therapeutic antibodies against the coronavirus disease 2019 (COVID-19) pandemic. Considering the mechanisms of hydrophobic interaction, hydration shell, surface tension, and the shielding effect of water molecules, this study reveals a hydrophobic-interaction-based mechanism by means of which SARS-CoV-2 S and ACE2 bind together in an aqueous environment. The hydrophobic interaction between the SARS-CoV-2 S and ACE2 protein is found to be significantly greater than that between SARS-CoV S and ACE2. At the docking site, the hydrophobic portions of the hydrophilic side chains of SARS-CoV-2 S are found to be involved in the hydrophobic interaction between SARS-CoV-2 S and ACE2. We propose a method to design live attenuated viruses by mutating several key amino acid residues of the spike protein to decrease the hydrophobic surface areas at the docking site. Mutation of a small amount of residues can greatly reduce the hydrophobic binding of the coronavirus to the receptor, which may be significant reduce infectivity and transmissibility of the virus.

q-bio.BM↗

arXiv2020

Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding

Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE. However, N-1, 1-N and N-N predictions still remain challenging. In this work, we propose a novel translational distance-based approach for knowledge graph link prediction. The proposed method includes two-folds, first we extend the RotatE from 2D complex domain to high dimension space with orthogonal transforms to model relations for better modeling capacity. Second, the graph context is explicitly modeled via two directed context representations. These context representations are used as part of the distance scoring function to measure the plausibility of the triples during training and inference. The proposed approach effectively improves prediction accuracy on the difficult N-1, 1-N and N-N cases for knowledge graph link prediction task. The experimental results show that it achieves better performance on two benchmark data sets compared to the baseline RotatE, especially on data set (FB15k-237) with many high in-degree connection nodes.

cs.CL↗

arXiv2020

Speaker Diarization with Lexical Information

This work presents a novel approach for speaker diarization to leverage lexical information provided by automatic speech recognition. We propose a speaker diarization system that can incorporate word-level speaker turn probabilities with speaker embeddings into a speaker clustering process to improve the overall diarization accuracy. To integrate lexical and acoustic information in a comprehensive way during clustering, we introduce an adjacency matrix integration for spectral clustering. Since words and word boundary information for word-level speaker turn probability estimation are provided by a speech recognition system, our proposed method works without any human intervention for manual transcriptions. We show that the proposed method improves diarization performance on various evaluation datasets compared to the baseline diarization system using acoustic information only in speaker embeddings.

eess.AS↗

arXiv2020

Multimodal Intelligence: Representation Learning, Information Fusion, and Applications

Deep learning methods have revolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial intelligence field involve multiple modalities. Therefore, it is of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities. In this paper, we provide a technical review of available models and learning methods for multimodal intelligence. The main focus of this review is the combination of vision and natural language modalities, which has become an important topic in both the computer vision and natural language processing research communities. This review provides a comprehensive analysis of recent works on multimodal deep learning from three perspectives: learning multimodal representations, fusing multimodal signals at various levels, and multimodal applications. Regarding multimodal representation learning, we review the key concepts of embedding, which unify multimodal signals into a single vector space and thereby enable cross-modality signal processing. We also review the properties of many types of embeddings that are constructed and learned for general downstream tasks. Regarding multimodal fusion, this review focuses on special architectures for the integration of representations of unimodal signals for a particular task. Regarding applications, selected areas of a broad interest in the current literature are covered, including image-to-text caption generation, text-to-image generation, and visual question answering. We believe that this review will facilitate future studies in the emerging field of multimodal intelligence for related communities.

cs.AI↗

arXiv2020

Graph Sequential Network for Reasoning over Sequences

Recently Graph Neural Network (GNN) has been applied successfully to various NLP tasks that require reasoning, such as multi-hop machine reading comprehension. In this paper, we consider a novel case where reasoning is needed over graphs built from sequences, i.e. graph nodes with sequence data. Existing GNN models fulfill this goal by first summarizing the node sequences into fixed-dimensional vectors, then applying GNN on these vectors. To avoid information loss inherent in the early summarization and make sequential labeling tasks on GNN output feasible, we propose a new type of GNN called Graph Sequential Network (GSN), which features a new message passing algorithm based on co-attention between a node and each of its neighbors. We validate the proposed GSN on two NLP tasks: interpretable multi-hop reading comprehension on HotpotQA and graph based fact verification on FEVER. Both tasks require reasoning over multiple documents or sentences. Our experimental results show that the proposed GSN attains better performance than the standard GNN based methods.

cs.CL↗

arXiv2020

The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service

Human conversations are complicated and building a human-like dialogue agent is an extremely challenging task. With the rapid development of deep learning techniques, data-driven models become more and more prevalent which need a huge amount of real conversation data. In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. The dataset reflects several characteristics of human-human conversations, e.g., goal-driven, and long-term dependency among the context. It also covers various dialogue types including task-oriented, chitchat and question-answering. Extra intent information and three well-annotated challenge sets are also provided. Then, we evaluate several retrieval-based and generative models to provide basic benchmark performance on the JDDC corpus. And we hope JDDC can serve as an effective testbed and benefit the development of fundamental research in dialogue task

cs.CL↗

arXiv2020

Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents

Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences. In this paper, we propose an effective and interpretable Select, Answer and Explain (SAE) system to solve the multi-document RC problem. Our system first filters out answer-unrelated documents and thus reduce the amount of distraction information. This is achieved by a document classifier trained with a novel pairwise learning-to-rank loss. The selected answer-related documents are then input to a model to jointly predict the answer and supporting sentences. The model is optimized with a multi-task learning objective on both token level for answer prediction and sentence level for supporting sentences prediction, together with an attention-based interaction between these two tasks. Evaluated on HotpotQA, a challenging multi-hop RC data set, the proposed SAE system achieves top competitive performance in distractor setting compared to other existing systems on the leaderboard.

cs.CL↗

arXiv2019

Trajectory tracking control for nonholonomic mobile robots under arbitrary reference input

This paper studies the tracking control problem for nonholonomic mobile robots based on second order dynamics, with application to consensus tracking and formation tracking. The greatest novelty in this paper is that the reference trajectory can be arbitrarily chosen, in the sense that the condition of persistency excitation and any other requirements are not imposed on the leader. In this paper, at first, the tracking control of one leader with single follower is taken into consideration, which is converted to the stabilization of two relative subsystems by the design of an adjoint system. Then, the single follower tracking controller is extended to the consensus tracking of multiple nonholonomic mobile robots connected by a directed acyclic graph, in which the convex combination in nonlinear manifolds is introduced to construct a virtual leader for each follower. Next, the relationship between consensus control and formation control is established for multiple nonholonomic mobile robots, with the result that a new transformed system is constructed so as to obtain the formation tracking control strategy from the consensus tracking result. Finally, simulations are presented to verify the effectiveness of the control laws.

eess.SY↗

arXiv2019

Preparation of a Heteronuclear Two-atom System in the 3D Motional Ground State in an Optical Tweezer

We report the realization of a heteronuclear two-atom of $^{87}$Rb-$^{85}$Rb in the ground state of an optical tweezer (OT). Starting by trapping two different isotopic single atoms, a $^{87}$Rb and a $^{85}$Rb in two strongly focused and linearly polarized OT with 4 $μ$m apart, we perform simultaneously three dimensional Raman sideband cooling for both atoms and the obtained 3D ground state probabilities of $^{87}$Rb and $^{85}$Rb are 0.91(5) and 0.91(10) respectively. There is no obvious crosstalk observed during the cooling process. We then merge them into one tweezer via a species-dependent transport, where the species-dependent potentials are made by changing the polarization of the OTs for each species from linear polarization to the desired circular polarization. The measurable increment of vibrational quantum due to merging is $0.013(1)$ for the axial dimension. This two-atom system can be used to investigate cold collisional physics, to form quantum logic gates, and to build a single heteronuclear molecule. It can also be scaled up to few-atom regime and extended to other atomic species and molecules, and thus to ultracold chemistry.

physics.atom-ph↗

arXiv2019

Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations

In vision-and-language grounding problems, fine-grained representations of the image are considered to be of paramount importance. Most of the current systems incorporate visual features and textual concepts as a sketch of an image. However, plainly inferred representations are usually undesirable in that they are composed of separate components, the relations of which are elusive. In this work, we aim at representing an image with a set of integrated visual regions and corresponding textual concepts, reflecting certain semantics. To this end, we build the Mutual Iterative Attention (MIA) module, which integrates correlated visual features and textual concepts, respectively, by aligning the two modalities. We evaluate the proposed approach on two representative vision-and-language grounding tasks, i.e., image captioning and visual question answering. In both tasks, the semantic-grounded image representations consistently boost the performance of the baseline models under all metrics across the board. The results demonstrate that our approach is effective and generalizes well to a wide range of models for image-related applications. (The code is available at https://github.com/fenglinliu98/MIA)

cs.CL↗

arXiv2019

Relation Module for Non-answerable Prediction on Question Answering

Machine reading comprehension(MRC) has attracted significant amounts of research attention recently, due to an increase of challenging reading comprehension datasets. In this paper, we aim to improve a MRC model's ability to determine whether a question has an answer in a given context (e.g. the recently proposed SQuAD 2.0 task). Our solution is a relation module that is adaptable to any MRC model. The relation module consists of both semantic extraction and relational information. We first extract high level semantics as objects from both question and context with multi-head self-attentive pooling. These semantic objects are then passed to a relation network, which generates relationship scores for each object pair in a sentence. These scores are used to determine whether a question is non-answerable. We test the relation module on the SQuAD 2.0 dataset using both BiDAF and BERT models as baseline readers. We obtain 1.8% gain of F1 on top of the BiDAF reader, and 1.0% on top of the BERT base model. These results show the effectiveness of our relation module on MRC

cs.CL↗

arXiv2019

Zero-shot Text-to-SQL Learning with Auxiliary Task

Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task. However, little work has paid attention to how these models generalize to realistic unseen data, which naturally raises a question: does this impressive performance signify a perfect generalization model, or are there still some limitations? In this paper, we first diagnose the bottleneck of text-to-SQL task by providing a new testbed, in which we observe that existing models present poor generalization ability on rarely-seen data. The above analysis encourages us to design a simple but effective auxiliary task, which serves as a supportive model as well as a regularization term to the generation task to increase the models generalization. Experimentally, We evaluate our models on a large text-to-SQL dataset WikiSQL. Compared to a strong baseline coarse-to-fine model, our models improve over the baseline by more than 3% absolute in accuracy on the whole dataset. More interestingly, on a zero-shot subset test of WikiSQL, our models achieve 5% absolute accuracy gain over the baseline, clearly demonstrating its superior generalizability.

cs.CL↗

arXiv2019

Revealing Energy Dependence of Quantum Defects via Two Heteronuclear Atoms in an Optical Tweezer

As a physically motivated and computationally simple model for cold atomic and molecular collisions, the multichannel quantum defect theory (MQDT) with frame transformation (FT) formalism provides an analytical treatment of scattering resonances in an arbitrary partial wave between alkali-metal atoms, leading to the experimental observation of $p-$ and $d-$wave resonances. However, the inconsistency of quantum defects for describing scattering resonances shows up when compared with experiments. Here, with two heteronuclear atoms in the ground state of an optical tweezer, the energy dependence of quantum defects is obviously revealed by comparing the measured s-wave scattering length with the prediction of MQDT-FT. By dividing the quantum defects into energy sensitive and insensitive categories, the inconsistency is ultimately removed while retaining the analytic structure of MQDT-FT. This study represents a significant improvement in the analytical MQDT-FT and demonstrates that a clean two-particle system is valuable to the test of collisional physics.

quant-ph↗