Search Results for author:
Found 363 papers, 185 papers with code
The Extended Parameter Filter
Drawing on an analogy to the extended Kalman filter, we develop and analyze, both theoretically and experimentally, a Taylor approximation to the parameter posterior that allows Storvik's method to be applied to a broader class of models.
Multilinear Dynamical Systems for Tensor Time Series
The MLDS models each time slice of the tensor time series as the multilinear projection of a corresponding member of a sequence of latent, low-dimensional tensors.
An Open Source Testing Tool for Evaluating Handwriting Input Methods
This paper presents an open source tool for testing the recognition accuracy of Chinese handwriting input methods.
Towards Practical Bayesian Parameter and State Estimation
Joint state and parameter estimation is a core problem for dynamic Bayesian networks.
CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
We propose CFO, a Conditional Focused neural-network-based approach to answering factoid questions with knowledge bases.
Swift: Compiled Inference for Probabilistic Programming Languages
A probabilistic program defines a probability measure over its semantic structures.
Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network
The qualitative and quantitative evaluations of experimental results indicate that the proposed method show a stable and prospective performance on artifacts reduction and detail recovery for limited angle tomography.
Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition
Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition.
Word Embedding and Topic Modeling Enhanced Multiple Features for Content Linking and Argument / Sentiment Labeling in Online Forums
Multiple grammatical and semantic features are adopted in content linking and argument/sentiment labeling for online forums in this paper.
On the diffusion approximation of nonconvex stochastic gradient descent
In addition, we discuss the effects of batch size for the deep neural networks, and we find that small batch size is helpful for SGD algorithms to escape unstable stationary points and sharp minimizers.
Fully Automatic Segmentation and Objective Assessment of Atrial Scars for Longstanding Persistent Atrial Fibrillation Patients Using Late Gadolinium-Enhanced MRI
In this study, we proposed a novel fully automatic pipeline to achieve an accurate and objective atrial scarring segmentation and assessment of LGE MRI scans for the AF patients.
SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation.
Enhancing Automatic ICD-9-CM Code Assignment for Medical Texts with PubMed
Frequent diseases often have more training data, which helps its classification to perform better than that of an infrequent disease.
Reinforced Co-Training
However, the selection of samples in existing co-training methods is based on a predetermined policy, which ignores the sampling bias between the unlabeled and the labeled subsets, and fails to explore the data space.
BRITS: Bidirectional Recurrent Imputation for Time Series
It is ubiquitous that time series contains many missing values.
General Classification
Multivariate Time Series Forecasting
+5
On Tree-Based Neural Sentence Modeling
To study the effectiveness of different tree structures, we replace the parsing trees with trivial trees (i. e., binary balanced tree, left-branching tree and right-branching tree) in the encoders.
Ranked #9 on
Sentiment Analysis
on Amazon Review Full
Atrial scars segmentation via potential learning in the graph-cuts framework
Late Gadolinium Enhancement Magnetic Resonance Imaging (LGE MRI) emerged as a routine scan for patients with atrial fibrillation (AF).
Atrial fibrosis quantification based on maximum likelihood estimator of multivariate images
We present a fully-automated segmentation and quantification of the left atrial (LA) fibrosis and scars combining two cardiac MRIs, one is the target late gadolinium-enhanced (LGE) image, and the other is an anatomical MRI from the same acquisition session.
Face Presentation Attack Detection in Learned Color-liked Space
Face presentation attack detection (PAD) has become a thorny problem for biometric systems and numerous countermeasures have been proposed to address it.
Face Presentation Attack Detection
Generative Adversarial Network
Towards Linear Time Neural Machine Translation with Capsule Networks
In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as \textsc{CapsNMT}.
CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling
In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements.
Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition
To bridge the gap between these two spaces in neural networks, we propose a neural line rasterization module to convert the vector sketch along with the attention estimated by RNN into a bitmap image, which is subsequently consumed by CNN.
Uniform-in-Time Weak Error Analysis for Stochastic Gradient Descent Algorithms via Diffusion Approximation
Diffusion approximation provides weak approximation for stochastic gradient descent algorithms in a finite time horizon.
A stochastic version of Stein Variational Gradient Descent for efficient sampling
We propose in this work RBM-SVGD, a stochastic version of Stein Variational Gradient Descent (SVGD) method for efficiently sampling from a given probability measure and thus useful for Bayesian inference.
Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge
This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017.
Atrial Scar Quantification via Multi-scale CNN in the Graph-cuts Framework
Compared with the conventional methods, which are based on the manual delineation of LA for initialization, our method is fully automatic and has demonstrated significantly better Dice score and accuracy (p < 0. 01).
A Sinogram Inpainting Method based on Generative Adversarial Network for Limited-angle Computed Tomography
Limited-angle computed tomography (CT) image reconstruction is a challenging reconstruction problem in the fields of CT. With the development of deep learning, the generative adversarial network (GAN) perform well in image restoration by approximating the distribution of training sample data.
Medical Physics
3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis
So, we propose a novel detection method for 3D face mask presentation attack by modeling reflectance differences based on intrinsic image analysis.
VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
We also introduce two tasks for video-and-language research based on VATEX: (1) Multilingual Video Captioning, aimed at describing a video in various languages with a compact unified captioning model, and (2) Video-guided Machine Translation, to translate a source language description into the target language using the video information as additional spatiotemporal context.
FoveaBox: Beyond Anchor-based Object Detector
In FoveaBox, an instance is assigned to adjacent feature levels to make the model more accurate. We demonstrate its effectiveness on standard benchmarks and report extensive experimental analysis.
Ranked #82 on
Object Detection
on COCO test-dev
(APM metric)
UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations
We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts.
Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
The visual storytelling (VST) task aims at generating a reasonable and coherent paragraph-level story with the image stream as input.
Ranked #21 on
Visual Storytelling
on VIST
Dynamically Fused Graph Network for Multi-hop Reasoning
However, many difficult questions require multiple supporting evidence from scattered text among two or more documents.
Ranked #33 on
Question Answering
on HotpotQA
Evidence for $Z_{c}^{\pm}$ decays into the $ρ^{\pm} η_{c}$ final state
We study $e^{+}e^{-}$ collisions with a $\pi^{+}\pi^{-}\pi^{0}\eta_{c}$ final state using data samples collected with the BESIII detector at center-of-mass energies $\sqrt{s}=4. 226$, $4. 258$, $4. 358$, $4. 416$, and $4. 600$ GeV.
High Energy Physics - Experiment
Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
To enhance the controllability and interpretability, one can replace the Gaussian prior with a mixture of Gaussian distributions (GM-VAE), whose mixture components could be related to hidden semantic aspects of data.
Deep Active Learning for Anchor User Prediction
Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction.
Enhancing Topic-to-Essay Generation with External Commonsense Knowledge
Experiments show that with external commonsense knowledge and adversarial training, the generated essays are more novel, diverse, and topic-consistent than existing methods in terms of both automatic and human evaluation.
Cross-Modal Commentator: Automatic Machine Commenting Based on Cross-Modal Information
Automatic commenting of online articles can provide additional opinions and facts to the reader, which improves user experience and engagement on social media platforms.
Generating Sentences from Disentangled Syntactic and Semantic Spaces
In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces.
Correct-and-Memorize: Learning to Translate from Interactive Revisions
Experiments in both ideal and real interactive translation settings demonstrate that our proposed \method enhances machine translation results significantly while requires fewer revision instructions from human compared to previous methods.
Automatic Generation of Personalized Comment Based on User Profile
Comments on social media are very diverse, in terms of content, style and vocabulary, which make generating comments much more challenging than other existing natural language generation~(NLG) tasks.
Towards Making the Most of BERT in Neural Machine Translation
Our experiments in machine translation show CTNMT gains of up to 3 BLEU score on the WMT14 English-German language pair which even surpasses the previous state-of-the-art pre-training aided NMT by 1. 4 BLEU score.
Self-reinforcing Unsupervised Matching
Remarkable gains in deep learning usually rely on tremendous supervised data.
Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus
MultiLing 2019 Headline Generation Task on Wikipedia Corpus raised a critical and practical problem: multilingual task on low resource corpus.
Effective Domain Knowledge Transfer with Soft Fine-tuning
However, the datasets from source domain are simply discarded in the fine-tuning process.
Task-Aware Monocular Depth Estimation for 3D Object Detection
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes
Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently.
PNAT: Non-autoregressive Transformer by Position Learning
However, position modeling of output words is an essential problem in non-autoregressive text generation.
Acutum: When Generalization Meets Adaptability
To the best of our knowledge, Acutum is the first adaptive gradient method without second moments.
Rethinking Text Attribute Transfer: A Lexical Analysis
We apply this framework to existing datasets and models and show that: (1) the pivot words are strong features for the classification of sentence attributes; (2) to change the attribute of a sentence, many datasets only requires to change certain pivot words; (3) consequently, many transfer models only perform the lexical-level modification, while leaving higher-level sentence structures unchanged.
On the convergence of gradient descent for two layer neural networks
It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points).
Cross-Lingual Vision-Language Navigation
Commanding a robot to navigate with natural language instructions is a long-term goal for grounded language understanding and robotics.
Pun-GAN: Generative Adversarial Network for Pun Generation
It consists of a generator to produce pun sentences, and a discriminator to distinguish between the generated pun sentences and the real sentences with specific word senses.
Variational Quantum Algorithms for Dimensionality Reduction and Classification
In this work, we present a quantum neighborhood preserving embedding and a quantum local discriminant embedding for dimensionality reduction and classification.
Kernelized Bayesian Softmax for Text Generation
Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase.
Importance-Aware Learning for Neural Headline Editing
We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers.
Non-autoregressive Transformer by Position Learning
Non-autoregressive models are promising on various text generation tasks.
SOLO: Segmenting Objects by Locations
We present a new, embarrassingly simple approach to instance segmentation in images.
Ranked #67 on
Instance Segmentation
on COCO test-dev
FoveaBox: Beyound Anchor-based Object Detection
While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors.
SketchDesc: Learning Local Sketch Descriptors for Multi-view Correspondence
In this paper, we study the problem of multi-view sketch correspondence, where we take as input multiple freehand sketches with different views of the same object and predict as output the semantic correspondence among the sketches.
Variational Template Machine for Data-to-Text Generation
We propose the variational template machine (VTM), a novel method to generate text descriptions from data tables.
SPAN: A Stochastic Projected Approximate Newton Method
SPAN computes the inverse of the Hessian matrix via low-rank approximation and stochastic Hessian-vector products.
End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds.
Ranked #5 on
Point Cloud Registration
on 3DMatch Benchmark
A random-batch Monte Carlo method for many-body systems with singular kernels
The cost of the rejection step is $O(1)$ since the interaction used is of short range.
Computational Physics Numerical Analysis Numerical Analysis 82B80, 60H35, 65C05
SOLOv2: Dynamic and Fast Instance Segmentation
Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.
Ranked #10 on
Real-time Instance Segmentation
on MSCOCO
TextGAIL: Generative Adversarial Imitation Learning for Text Generation
Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts.
Cross-lingual Supervision Improves Unsupervised Neural Machine Translation
Neural machine translation~(NMT) is ineffective for zero-resource languages.
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space
We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently.
Mirror-Generative Neural Machine Translation
Training neural machine translation models (NMT) requires a large amount of parallel corpus, which is scarce for many language pairs.
ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization
Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence.
Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs
Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency.
Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge
In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR.
Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention
Compared to conventional binary label based loss, the proposed SE loss can reduce noisy patches in the resulting segmentation, which is commonly seen for deep learning-based methods.
XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference
We therefore propose a novel model, XREF, that leverages attention mechanisms to (1) pinpoint relevant context within comments, and (2) detect supporting entities from the news article.
Model independent determination of the spin of the $Ω^{-}$ and its polarization alignment in $ψ(3686)\rightarrowΩ^{-}\barΩ^{+}$
We present an analysis of the process $\psi(3686) \to \Omega^- \bar{\Omega}^+$ ($\Omega^-\to K^-\Lambda$, $\bar{\Omega}^+\to K^+\bar{\Lambda}$, $\Lambda\to p\pi^-$, $\bar{\Lambda}\to \bar{p}\pi^+$) based on a data set of $448\times 10^6$ $\psi(3686)$ decays collected with the BESIII detector at the BEPCII electron-positron collider.
High Energy Physics - Experiment
Xiaomingbot: A Multilingual Robot News Reporter
This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation.
Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation
Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios.
Do You Have the Right Scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods
It has been a common approach to pre-train a language model on a large corpus and fine-tune it on task-specific data.
Generating Fluent Adversarial Examples for Natural Languages
Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge.
AtrialJSQnet: A New Framework for Joint Segmentation and Quantification of Left Atrium and Scars Incorporating Spatial and Shape Information
In this work, we develop a new framework, namely AtrialJSQnet, where LA segmentation, scar projection onto the LA surface, and scar quantification are performed simultaneously in an end-to-end style.
Cross-Modality Multi-Atlas Segmentation Using Deep Neural Networks
For label fusion, we adapt a few-shot learning network to measure the similarity of atlas and target patches.
Deep Modulation Recognition with Multiple Receive Antennas: An End-to-end Feature Learning Approach
The first is based on multi-view convolutional neural network by treating signals from different receive antennas as different views of a 3D object and designing the location and operation of view-pooling layer that are suitable for feature fusion of multi-antenna signals.
Glancing Transformer for Non-Autoregressive Neural Machine Translation
With GLM, we develop Glancing Transformer (GLAT) for machine translation.
Ranked #69 on
Machine Translation
on WMT2014 English-German
3rd Place Solution to "Google Landmark Retrieval 2020"
Image retrieval is a fundamental problem in computer vision.
Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information
As the target domain could be unknown, we randomly generate a modality vector for the target modality in the style transfer stage, to simulate the domain shift for unknown domains.
Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation
At top of the MoE layer, we deploy a transformer layer for each task as task tower to learn task-specific information.
Generative Imagination Elevates Machine Translation
Given a sentence in a source language, whether depicting the visual scene helps translation into a target language?
Ranked #7 on
Multimodal Machine Translation
on Multi30K
"Listen, Understand and Translate": Triple Supervision Decouples End-to-end Speech-to-text Translation
Can we build a system to fully utilize signals in a parallel ST corpus?
Consecutive Decoding for Speech-to-text Translation
The key idea is to generate source transcript and target translation text with a single decoder.
Double Graph Based Reasoning for Document-level Relation Extraction
Document-level relation extraction aims to extract relations among entities within a document.
Ranked #12 on
Relation Extraction
on DocRED
A random batch Ewald method for particle systems with Coulomb interactions
We develop a random batch Ewald (RBE) method for molecular dynamics simulations of particle systems with long-range Coulomb interactions, which achieves an $O(N)$ complexity in each step of simulating the $N$-body systems.
Computational Physics 65C35, 82M37, 65T50
Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs?
Ranked #3 on
Machine Translation
on WMT2014 English-French
(using extra training data)
Rethinking Document-level Neural Machine Translation
This paper does not aim at introducing a novel model for document-level neural machine translation.
LightSeq: A High Performance Inference Library for Transformers
Transformer, BERT and their variants have achieved great success in natural language processing.
Volctrans Parallel Corpus Filtering System for WMT 2020
In this paper, we describe our submissions to the WMT20 shared task on parallel corpus filtering and alignment for low-resource conditions.
The Volctrans Machine Translation System for WMT20
This paper describes our VolcTrans system on WMT20 shared news translation task.
Brain Tumor Segmentation Network Using Attention-based Fusion and Spatial Relationship Constraint
Considering that multi-modal MR images can reflect different tumor biological properties, we develop a novel multi-modal tumor segmentation network (MMTSN) to robustly segment brain tumors based on multi-modal MR images.
On the Sentence Embeddings from Pre-trained Language Models
Pre-trained contextual representations like BERT have achieved great success in natural language processing.
Ranked #16 on
Semantic Textual Similarity
on STS16
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin.
DmifNet:3D Shape Reconstruction Based on Dynamic Multi-Branch Information Fusion
Then, we use a separate side branch network to process the extracted data to better capture edge geometry and corners feature information.
Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach
Generating natural language under complex constraints is a principled formulation towards controllable text generation.
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location.
Ranked #5 on
2D Object Detection
on CeyMo
Search for the reaction $e^{+}e^{-} \rightarrow π^{+}π^{-} χ_{cJ}$ and a charmonium-like structure decaying to $χ_{cJ}π^{\pm}$ between 4.18 and 4.60 GeV
We search for the process $e^{+}e^{-}\rightarrow \pi ^{+}\pi ^{-} \chi_{cJ}$ ($J=0, 1, 2$) and for a charged charmonium-like state in the $\pi ^{\pm} \chi_{cJ}$ subsystem.
High Energy Physics - Experiment
Reciprocal Supervised Learning Improves Neural Machine Translation
Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT).
Trustworthy Preference Completion in Social Choice
As from time to time it is impractical to ask agents to provide linear orders over all alternatives, for these partial rankings it is necessary to conduct preference completion.
Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification
Graph Contrastive Learning (GCL) has proven highly effective in promoting the performance of Semi-Supervised Node Classification (SSNC).
NeurST: Neural Speech Translation Toolkit
NeurST is an open-source toolkit for neural speech translation.
Ranked #1 on
Speech-to-Text Translation
on libri-trans
Finding Sparse Structures for Domain Specific Neural Machine Translation
Neural machine translation often adopts the fine-tuning approach to adapt to specific domains.
LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
The final claim verification is based on all latent variables.
Measurements of the center-of-mass energies of $e^{+}e^{-}$ collisions at BESIII
During the 2016-17 and 2018-19 running periods, the BESIII experiment collected 7. 5~fb$^{-1}$ of $e^+e^-$ collision data at center-of-mass energies ranging from 4. 13 to 4. 44 GeV.
High Energy Physics - Experiment
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade
On the other hand, the exiting decisions made by internal classifiers are unreliable, leading to wrongly emitted early predictions.
Vocabulary Learning via Optimal Transport for Neural Machine Translation
The choice of token vocabulary affects the performance of machine translation.
High-Likelihood Area Matters --- Rewarding Near-Correct Predictions Under Imbalanced Distributions
We find in practice that the high-likelihood area contains correct predictions for tail classes and it plays a vital role in learning imbalanced class distributions.
Non-iterative Parallel Text Generation via Glancing Transformer
Although non-autoregressive models with one-iteration generation achieves remarkable inference speed-up, they still falls behind their autoregressive counterparts inprediction accuracy.
Information-theoretic Vocabularization via Optimal Transport
In this paper, we find an exciting relation between an information-theoretic feature and the performance of NLP tasks such as machine translation with a given vocabulary.
Learning from deep model via exploring local targets
However, it has been observed that a converged heavy teacher model is strongly constrained for learning a compact student network and could make the optimization subject to poor local optima.
Adaptive Gradient Methods Can Be Provably Faster than SGD with Random Shuffling
Adaptive gradient methods have been shown to outperform SGD in many tasks of training neural networks.
Taxonomy Completion via Triplet Matching Network
Previous approaches focus on the taxonomy expansion, i. e. finding an appropriate hypernym concept from the taxonomy for a new query concept.
Triangular Bidword Generation for Sponsored Search Auction
Our proposed model is simple yet effective: by using bidword as the bridge between search query and advertisement, the generation of search query, advertisement and bidword can be jointly learned in the triangular training framework.
On the Relationship between Explanation and Recommendation: Learning to Rank Explanations for Improved Performance
Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS).
Cross section measurement of $e^+e^- \to p\bar{p}η$ and $e^+e^- \to p\bar{p}ω$ at center-of-mass energies between 3.773 GeV and 4.6 GeV
Based on $14. 7~\textrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected with the BESIII detector at the BEPCII collider at 17 different center-of-mass energies between $3. 7730~\textrm{GeV}$ and $4. 5995~\textrm{GeV}$, Born cross sections of the two processes $e^+e^- \to p\bar{p}\eta$ and $e^+e^- \to p\bar{p}\omega$ are measured for the first time.
High Energy Physics - Experiment
EXTRA: Explanation Ranking Datasets for Explainable Recommendation
To achieve a standard way of evaluating recommendation explanations, we provide three benchmark datasets for EXplanaTion RAnking (denoted as EXTRA), on which explainability can be measured by ranking-oriented metrics.
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration.
MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
Searching for novel molecules with desired chemical properties is crucial in drug discovery.
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples.
Locate then Segment: A Strong Pipeline for Referring Image Segmentation
Referring image segmentation aims to segment the objects referred by a natural language expression.
Generalized Referring Expression Segmentation
Image Segmentation
+2
Progressive Domain Expansion Network for Single Domain Generalization
A series of strategies are introduced to guarantee the safety and effectiveness of the expanded domains.
Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
Scale-aware Automatic Augmentation for Object Detection
We propose Scale-aware AutoAug to learn data augmentation policies for object detection.
ENPAR:Enhancing Entity and Entity Pair Representations for Joint Entity Relation Extraction
Current state-of-the-art systems for joint entity relation extraction (Luan et al., 2019; Wad-den et al., 2019) usually adopt the multi-task learning framework.
Few-Shot Meta-Learning on Point Cloud for Semantic Segmentation
With a good understanding of environmental information, construction robots can work better.
Counter-Interference Adapter for Multilingual Machine Translation
Developing a unified multilingual model has long been a pursuit for machine translation.
End-to-end Speech Translation via Cross-modal Progressive Training
XSTNet takes both speech and text as input and outputs both transcription and translation text.
Learning Shared Semantic Space for Speech-to-Text Translation
By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art.
Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
Thus REDER enables reversible machine translation by simply flipping the input and output ends.
The Volctrans Neural Speech Translation System for IWSLT 2021
For offline speech translation, our best end-to-end model achieves 8. 1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution.
Unsupervised Multi-Modality Registration Network based on Spatially Encoded Gradient Information
However, it is still challenging to develop a multi-modality registration network due to the lack of robust criteria for network training.
Learning Language Specific Sub-network for Multilingual Machine Translation
These jointly trained models often suffer from performance degradation on rich-resource language pairs.
Contrastive Learning for Many-to-many Multilingual Neural Machine Translation
Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind.
Personalized Transformer for Explainable Recommendation
Transformer, which is demonstrated with strong language modeling capability, however, is not personalized and fails to make use of the user and item IDs since the ID tokens are not even in the same semantic space as the words.
Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge
Knowledge facts are typically represented by relational triples, while we observe that some commonsense facts are represented by the triples whose forms are inconsistent with the expression of language.
Cysteine post-translational modifications: ten years from chemical proteomics to bioinformatics
As the only thiol-bearing amino acid, cysteine (Cys) residues in proteins have the reactive thiol side chain, which is susceptible to a series of post-translational modifications (PTMs).
Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker
Existing methods are not effective due to two challenges of this task: a) the target event arguments are scattered across sentences; b) the correlation among events in a document is non-trivial to model.
Ranked #2 on
Document-level Event Extraction
on ChFinAnn
Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation
In this paper, we tackle the task of Definition Generation (DG) in Chinese, which aims at automatically generating a definition for a word.
Autocorrect in the Process of Translation --- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction
Keyphrase Prediction (KP) task aims at predicting several keyphrases that can summarize the main idea of the given document.
Adversarial Option-Aware Hierarchical Imitation Learning
In particular, we propose an Expectation-Maximization(EM)-style algorithm: an E-step that samples the options of expert conditioned on the current learned policy, and an M-step that updates the low- and high-level policies of agent simultaneously to minimize the newly proposed option-occupancy measurement between the expert and the agent.
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice.
Ranked #1 on
Semantic Similarity
on CHIP-STS
Language Tags Matter for Zero-Shot Neural Machine Translation
Language tag (LT) strategies are often adopted to indicate the translation directions in MNMT.
Learning to Disentangle GAN Fingerprint for Fake Image Attribution
Adopting a multi-task framework, we propose a GAN Fingerprint Disentangling Network (GFD-Net) to simultaneously disentangle the fingerprint from GAN-generated images and produce a content-irrelevant representation for fake image attribution.
AtrialGeneral: Domain Generalization for Left Atrial Segmentation of Multi-Center LGE MRIs
Left atrial (LA) segmentation from late gadolinium enhanced magnetic resonance imaging (LGE MRI) is a crucial step needed for planning the treatment of atrial fibrillation.
Subjective Bias in Abstractive Summarization
Due to the subjectivity of the summarization, it is a good practice to have more than one gold summary for each training document.
Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review
Late gadolinium enhancement magnetic resonance imaging (LGE MRI) is commonly used to visualize and quantify left atrial (LA) scars.
SOLO: A Simple Framework for Instance Segmentation
Besides instance segmentation, our method yields state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation.
Probabilistic Graph Reasoning for Natural Proof Generation
In this paper, we propose PRobr, a novel approach for joint answer prediction and proof generation.
UniRE: A Unified Label Space for Entity Relation Extraction
Entities and relations are represented by squares and rectangles in the table.
Automatic Fatou Property of Law-invariant Risk Measures
In the paper we investigate automatic Fatou property of law-invariant risk measures on a rearrangement-invariant function space $\mathcal{X}$ other than $L^\infty$.
Follow Your Path: a Progressive Method for Knowledge Distillation
However, it has been observed that a converged heavy teacher model is strongly constrained for learning a compact student network and could make the optimization subject to poor local optima.
Pre-training Methods for Neural Machine Translation
This tutorial provides a comprehensive guide to make the most of pre-training for neural machine translation.
Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation
In a unified framework, we jointly predict the feasible 6-DoF grasp poses, instance semantic segmentation, and collision information.
WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration
Instead of using a predefined fixed-size local support in voxelization, we propose to learn the optimal support in a data-driven manner.
Learning to Design and Construct Bridge without Blueprint
In this task, the robot needs to first design a feasible bridge architecture for arbitrarily wide cliffs and then manipulate the blocks reliably to construct a stable bridge according to the proposed design.
MTG: A Benchmark Suite for Multilingual Text Generation
We introduce MTG, a new benchmark suite for training and evaluating multilingual text generation.
ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation
Separating 3D point clouds into individual instances is an important task for 3D vision.
Secoco: Self-Correcting Encoding for Neural Machine Translation
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting
Most NER methods rely on extensive labeled data for model training, which struggles in the low-resource scenarios with limited training data.
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification
Data augmentation aims to enrich training samples for alleviating the overfitting issue in low-resource or class-imbalanced situations.
Right Ventricular Segmentation from Short- and Long-Axis MRIs via Information Transition
In this work, we propose an automatic RV segmentation framework, where the information from long-axis (LA) views is utilized to assist the segmentation of short-axis (SA) views via information transition.
Multilingual Translation via Grafting Pre-trained Language Models
Can pre-trained BERT for one language and GPT for another be glued together to translate texts?
Learning When to Translate for Streaming Speech
Given a usually long speech sequence, we develop an efficient monotonic segmentation module inside an encoder-decoder model to accumulate acoustic information incrementally and detect proper speech unit boundaries for the input in speech translation task.
Learning Kernel-Smoothed Machine Translation with Retrieved Examples
How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining?
Dynamic Knowledge Distillation for Pre-trained Language Models
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models.
The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation.
Knowledge Guided Geometric Editing for Unsupervised Drug Design
Deep learning models have been widely used in automatic drug design.
Non-Autoregressive Models are Better Multilingual Translators
Multilingual machine translation aims to develop a single model for multiple language directions.
NAIL: A Challenging Benchmark for Na\"ive Logical Reasoning
Logical reasoning over natural text is an important capability towards human level intelligence.
Generating Antimicrobial Peptides from Latent Secondary Structure Space
By sampling in the latent secondary structure space, we can generate peptides with ideal amino acids and secondary structures at the same time.
LightSeq2: Accelerated Training for Transformer-based Models on GPUs
In this paper, we present LightSeq2, a system to accelerate training for a general family of Transformer models on GPUs.
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundary.
Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
How do we perform efficient inference while retaining high translation quality?
CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
In this paper, we present a large-scale Chinese news summarization dataset CNewSum, which consists of 304, 307 documents and human-written summaries for the news feed.
Self-Supervised Speech Denoising Using Only Noisy Audio Signals
The first module adopts a random audio sub-sampler on each noisy audio to generate training pairs.
Multi-Modality Cardiac Image Analysis with Deep Learning
Accurate cardiac computing, analysis and modeling from multi-modality images are important for the diagnosis and treatment of cardiac disease.
A Survey on Green Deep Learning
In recent years, larger and deeper models are springing up and continuously pushing state-of-the-art (SOTA) results across various fields like natural language processing (NLP) and computer vision (CV).
Learning Logic Rules for Document-level Relation Extraction
LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor.
Ranked #21 on
Relation Extraction
on DocRED
StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks
Scene text detection is still a challenging task, as there may be extremely small or low-resolution strokes, and close or arbitrary-shaped texts.
Unsupervised Editing for Counterfactual Stories
We also propose a new metric to alleviate the shortcomings of current automatic metrics and better evaluate the trade-off.
Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly reduce the retraining computational cost and the potential environmental side-effects.
Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass
Quantification of forest biomass stocks and their dynamics is important for implementing effective climate change mitigation measures.
MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images
Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on myocardium is the key to this assessment.
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population.
AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images
Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods.
Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion
For the label fusion, we design a similarity estimation network (SimNet), which estimates the fusion weight of each atlas by measuring its similarity to the target image.
Personalized Prompt Learning for Explainable Recommendation
In the latter case, ID vectors are randomly initialized but the model is trained in advance on large corpora, so they are actually in different learning stages.
KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models
However, to figure out whether PLMs can be reliable knowledge sources and used as alternative knowledge bases (KBs), we need to further explore some critical features of PLMs.
