Search Results for author:
Found 89 papers, 41 papers with code
MR-P: A Parallel Decoding Algorithm for Iterative Refinement Non-Autoregressive Translation
The Conditional Masked Language Model (CMLM) is a strong baseline of NAT.
Self-Verification Improves Few-Shot Clinical Information Extraction
Extracting patient information from unstructured text is a critical task in health decision-support and clinical research.
Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding
Scientific literature understanding tasks have gained significant attention due to their potential to accelerate scientific discovery.
Chain-of-Skills: A Configurable Model for Open-domain Question Answering
Our approach outperforms recent self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.
Ranked #4 on
Question Answering
on HotpotQA
End-to-end Training and Decoding for Pivot-based Cascaded Translation Model
Utilizing pivot language effectively can significantly improve low-resource machine translation.
Evaluating the Efficacy of Length-Controllable Machine Translation
We can use automatic summarization or machine translation evaluation metrics for length-controllable machine translation, but this is not necessarily suitable and accurate.
Improve Video Representation with Temporal Adversarial Augmentation
In this paper, we introduce Temporal Adversarial Augmentation (TA), a novel video augmentation technique that utilizes temporal attention.
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
Chameleon synthesizes programs by composing various tools (e. g., LLMs, off-the-shelf vision models, web search engines, Python functions, and heuristic-based modules) for accomplishing complex reasoning tasks.
Pre-training Transformers for Knowledge Graph Completion
Learning transferable representation of knowledge graphs (KGs) is challenging due to the heterogeneous, multi-relational nature of graph structures.
LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints
Trajectory prediction for autonomous driving must continuously reason the motion stochasticity of road agents and comply with scene constraints.
Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e. g., task-oriented dialog and question answering.
ForceFormer: Exploring Social Force and Transformer for Pedestrian Trajectory Prediction
Predicting trajectories of pedestrians based on goal information in highly interactive scenes is a crucial step toward Intelligent Transportation Systems and Autonomous Driving.
Generating Evidential BEV Maps in Continuous Driving Space
Safety is critical for autonomous driving, and one aspect of improving safety is to accurately capture the uncertainties of the perception system, especially knowing the unknown.
ShadowFormer: Global Context Helps Image Shadow Removal
It is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions.
Ranked #1 on
Shadow Removal
on Adjusted ISTD
Language Models as Inductive Reasoners
To this end, we propose a new task, which is to induce natural language rules from natural language facts, and create a dataset termed DEER containing 1. 2k rule-fact pairs for the task, where rules and facts are written in natural language.
Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge
We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources.
ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizations
Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware.
Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering
Given its effectiveness on knowledge-intensive natural language processing tasks, dense retrieval models have become increasingly popular.
Vertical Semi-Federated Learning for Efficient Online Advertising
As an emerging secure learning paradigm in leveraging cross-silo private data, vertical federated learning (VFL) is expected to improve advertising models by enabling the joint learning of complementary user attributes privately owned by the advertiser and the publisher.
Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed
Recently, Diffenderfer and Kailkhura proposed a new paradigm for learning compact yet highly accurate binary neural networks simply by pruning and quantizing randomly weighted full precision neural networks.
GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Model
Our model achieves performance on par with the state-of-the-art models at a much higher prediction speed tested on multiple open datasets.
Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning
We present a bi-encoder framework for named entity recognition (NER), which applies contrastive learning to map candidate text spans and entity types into the same vector representation space.
Ranked #1 on
Named Entity Recognition (NER)
on BC5CDR
INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
In an information-seeking conversation, a user converses with an agent to ask a series of questions that can often be under- or over-specified.
READ: Aggregating Reconstruction Error into Out-of-distribution Detection
We propose a novel method, READ (Reconstruction Error Aggregated Detector), to unify inconsistencies from classifier and autoencoder.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Achieving Lightweight Federated Advertising with Self-Supervised Split Distillation
As an emerging secure learning paradigm in leveraging cross-agency private data, vertical federated learning (VFL) is expected to improve advertising models by enabling the joint learning of complementary user attributes privately owned by the advertiser and the publisher.
Unsupervised Learning of Hierarchical Conversation Structure
Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization.
Visually-Augmented Language Modeling
With the visually-augmented context, VaLM uses a visual knowledge fusion layer to enable multimodal grounded language modeling by attending to both text context and visual knowledge in images.
Mitigating Neural Network Overconfidence with Logit Normalization
Our method is motivated by the analysis that the norm of the logit keeps increasing during training, leading to overconfident output.
A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models
With the increasing of model capacity brought by pre-trained language models, there emerges boosting needs for more knowledgeable natural language processing (NLP) models with advanced functionalities including providing and making flexible use of encyclopedic and commonsense knowledge.
Identifiability of Label Noise Transition Matrix
When label noise transition depends on each instance, the problem of identifying the instance-dependent noise transition matrix becomes substantially more challenging.
Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing
Overall, domainspecific vocabulary and pretraining facilitate more robust models for fine-tuning.
Knowledge-Rich Self-Supervision for Biomedical Entity Linking
Zero-shot entity linking has emerged as a promising direction for generalizing to new entities, but it still requires example gold entity mentions during training and canonical descriptions for all entities, both of which are rarely available outside of Wikipedia.
Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise
We show that our method successfully alleviates the damage of both label noise and confirmation bias.
Ranked #2 on
Image Classification
on mini WebVision 1.0
Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities.
Ranked #2 on
Common Sense Reasoning
on CommonsenseQA
(using extra training data)
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
We demonstrate that while recent models reach human performance when they have access to large amounts of labeled data, there is a huge gap in performance in the few-shot setting for most tasks.
RMNet: Equivalently Removing Residual Connection from Networks
In this paper, we aim to remedy this problem and propose to remove the residual connection in a vanilla ResNet equivalently by a reserving and merging (RM) operation on ResBlock.
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
These observations require us to rethink the treatment of noisy labels, and we hope the availability of these two datasets would facilitate the development and evaluation of future learning with noisy label solutions.
Mitigating Memorization of Noisy Labels via Regularization between Representations
Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs).
Open Domain Question Answering with A Unified Knowledge Interface
The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge.
A Good Representation Detects Noisy Labels
In this paper, given good representations, we propose a universally applicable and training-free solution to detect noisy labels.
Disentangled Feature Representation for Few-shot Image Classification
In this work, we propose a novel Disentangled Feature Representation framework, dubbed DFR, for few-shot learning applications.
Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving
Sharing collective perception messages (CPM) between vehicles is investigated to decrease occlusions so as to improve the perception accuracy and safety of autonomous driving.
Dialogue State Tracking with a Language Model using Schema-Driven Prompting
Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots.
Ranked #1 on
Dialogue State Tracking
on MULTIWOZ 2.1
(MultiWOZ (Joint Goal Acc) metric)
Variational Disentanglement for Domain Generalization
Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain.
Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature
A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months.
Reconciliation of Statistical and Spatial Sparsity For Robust Image and Image-Set Classification
Recent image classification algorithms, by learning deep features from large-scale datasets, have achieved significantly better results comparing to the classic feature-based approaches.
CNN Retrieval based Unsupervised Metric Learning for Near-Duplicated Video Retrieval
As important data carriers, the drastically increasing number of multimedia videos often brings many duplicate and near-duplicate videos in the top results of search.
Interaction Detection Between Vehicles and Vulnerable Road Users: A Deep Generative Approach with Attention
Intersections where vehicles are permitted to turn and interact with vulnerable road users (VRUs) like pedestrians and cyclists are among some of the most challenging locations for automated and accurate recognition of road users' behavior.
Mixture of Robust Experts (MoRE):A Robust Denoising Method towards multiple perturbations
To tackle the susceptibility of deep neural networks to examples, the adversarial training has been proposed which provides a notion of robust through an inner maximization problem presenting the first-order embedded within the outer minimization of the training loss.
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
Specifically, we find the final embedding obtained by the mainstream SSL methods contains the most fruitful information, and propose to distill the final embedding to maximally transmit a teacher's knowledge to a lightweight model by constraining the last embedding of the student to be consistent with that of the teacher.
Targeted Adversarial Training for Natural Language Understanding
We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding.
An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
Pseudo-labeling (PL) and Data Augmentation-based Consistency Training (DACT) are two approaches widely used in Semi-Supervised Learning (SSL) methods.
Joint Dimensionality Reduction for Separable Embedding Estimation
In this paper, we propose a supervised dimensionality reduction method that learns linear embeddings jointly for two feature vectors representing data of different modalities or data from distinct types of entities.
UnitedQA: A Hybrid Approach for Open Domain Question Answering
To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively.
Ranked #1 on
Open-Domain Question Answering
on TriviaQA
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020.
One for More: Selecting Generalizable Samples for Generalizable ReID Model
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch.
Train Once, and Decode As You Like
In this paper we propose a unified approach for supporting different generation manners of machine translation, including autoregressive, semi-autoregressive, and refinement-based non-autoregressive models.
Exploring Dynamic Context for Multi-path Trajectory Prediction
In our framework, first, the spatial context between agents is explored by using self-attention architectures.
Posterior Differential Regularization with f-divergence for Improving Model Robustness
Theoretically, we provide a connection of two recent methods, Jacobian Regularization and Virtual Adversarial Training, under this framework.
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting.
Image Classification with Label Noise
Learning with noisy labels
Pruning Filter in Filter
Through extensive experiments, we demonstrate that SWP is more effective compared to the previous FP-based methods and achieves the state-of-art pruning ratio on CIFAR-10 and ImageNet datasets without obvious accuracy drop.
Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Then we force the model to pull the feature of the distracting video and the feature of the original video closer, so that the model is explicitly restricted to resist the background influence, focusing more on the motion changes.
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual.
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
In this paper, we challenge this assumption by showing that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models.
Ranked #1 on
Named Entity Recognition
on JNLPBA
Intrinsic radiation background of LaBr$_3$(Ce) detector via coincidence measurements and simulations
The LaBr$_3$(Ce) detector has attracted much attention in recent years for its superior characteristics to other scintillating materials in terms of resolution and efficiency.
Instrumentation and Detectors Nuclear Experiment
Attentive Graph Neural Networks for Few-Shot Learning
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks.
AMENet: Attentive Maps Encoder Network for Trajectory Prediction
Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic.
Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering
We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings.
Filter Grafting for Deep Neural Networks: Reason, Method, and Cultivation
To gain a universal improvement on both valid and invalid filters, we compensate grafting with distillation (\textbf{Cultivation}) to overcome the drawback of grafting .
Adversarial Training for Large Neural Language Models
In natural language processing (NLP), pre-training large neural language models such as BERT have demonstrated impressive gain in generalization for a variety of tasks, with further improvement from adversarial fine-tuning.
Ranked #4 on
Natural Language Inference
on ANLI test
(using extra training data)
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models.
MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
In inference time, we combine the past context and motion information of the target agent with samplings of the latent variables to predict multiple realistic trajectories in the future.
Filter Grafting for Deep Neural Networks
To better perform the grafting process, we develop an entropy-based criterion to measure the information of filters and an adaptive weighting strategy for balancing the grafted information among networks.
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
This procedure encourages that the selected training samples can be both clean and miscellaneous, and that the two models can promote each other iteratively.
Ranked #9 on
Unsupervised Domain Adaptation
on Market to Duke
Interpretable Text Classification Using CNN and Max-pooling
Deep neural networks have been widely used in text classification.
Many could be better than all: A novel instance-oriented algorithm for Multi-modal Multi-label problem
The quality of data collected from different channels are inconsistent and some of them may not benefit for prediction.
Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks
We propose a new learning paradigm, Local to Global Learning (LGL), for Deep Neural Networks (DNNs) to improve the performance of classification problems.
A Dynamic Speaker Model for Conversational Interactions
Characterizing these differences can be useful in human-computer interaction, as well as analysis of human-human conversations.
Improving Span-based Question Answering Systems with Coarsely Labeled Data
We study approaches to improve fine-grained short answer Question Answering models by integrating coarse-grained data annotated for paragraph-level relevance and show that coarsely annotated data can bring significant performance gains.
Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane
Inspired by the pioneering work of information bottleneck principle for Deep Neural Networks (DNNs) analysis, we design an information plane based framework to evaluate the capability of DNNs for image classification tasks, which not only helps understand the capability of DNNs, but also helps us choose a neural network which leads to higher classification accuracy more efficiently.
Sounding Board: A User-Centric and Content-Driven Social Chatbot
We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize.
A Factored Neural Network Model for Characterizing Online Discussions in Vector Space
We develop a novel factored neural model that learns comment embeddings in an unsupervised way leveraging the structure of distributional context in online discussion forums.
Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
Many social media platforms offer a mechanism for readers to react to comments, both positively and negatively, which in aggregate can be thought of as community endorsement.
Bi-directional Attention with Agreement for Dependency Parsing
We develop a novel bi-directional attention model for dependency parsing, which learns to agree on headword predictions from the forward and backward parsing directions.
Ranked #4 on
Chinese Dependency Parsing
on Chinese Pennbank
Language Models for Image Captioning: The Quirks and What Works
Two recent approaches have achieved state-of-the-art results in image captioning.
Convex Two-Layer Modeling
Latent variable prediction models, such as multi-layer networks, impose auxiliary latent variables between inputs and outputs to allow automatic inference of implicit features useful for prediction.
Convex Relaxations of Bregman Divergence Clustering
Although many convex relaxations of clustering have been proposed in the past decade, current formulations remain restricted to spherical Gaussian or discriminative models and are susceptible to imbalanced clusters.
