Search Results for author:
Found 71 papers, 38 papers with code
A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple-wise Perspective in Angular Space
Learning high-quality sentence representations is a fundamental problem of natural language processing which could benefit a wide range of downstream tasks.
Overview of the MEDIQA 2021 Shared Task on Summarization in the Medical Domain
The MEDIQA 2021 shared tasks at the BioNLP 2021 workshop addressed three tasks on summarization for medical text: (i) a question summarization task aimed at exploring new approaches to understanding complex real-world consumer health queries, (ii) a multi-answer summarization task that targeted aggregation of multiple relevant answers to a biomedical question into one concise and relevant answer, and (iii) a radiology report summarization task addressing the development of clinically relevant impressions from radiology report findings.
The NiuTrans’s Submission to the IWSLT22 English-to-Chinese Offline Speech Translation Task
This paper describes NiuTrans’s submission to the IWSLT22 English-to-Chinese (En-Zh) offline speech translation task.
The NiuTrans Machine Translation Systems for WMT20
This paper describes NiuTrans neural machine translation systems of the WMT20 news translation tasks.
Adaptive Deep Reasoning: Triggering Deep Thinking When Needed
More recent approaches have attempted to integrate long-chain and short-chain reasoning abilities into a single model, yet they still rely on manual control to toggle between short and long CoT.
Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
We propose the unit language to overcome the two modeling challenges.
Anymate: A Dataset and Baselines for Learning 3D Object Rigging
Rigging and skinning are essential steps to create realistic 3D animations, often requiring significant expertise and manual effort.
UNILoc: Unified Localization Combining Model-Based Geometry and Unsupervised Learning
Accurate mobile device localization is critical for emerging 5G/6G applications such as autonomous vehicles and augmented reality.
Ga$_2$O$_3$ TCAD Mobility Parameter Calibration using Simulation Augmented Machine Learning with Physics Informed Neural Network
Schottky Barrier Diode (SBD) fabricated with emerging ultra-wide-bandgap material, Gallium Oxide (Ga$_2$O$_3$), is measured and its current-voltage (IV) is used for Ga$_2$O$_3$ Philips Unified Mobility (PhuMob) model parameters, effective anode workfunction, and ambient temperature extraction (7 parameters).
Model Predictive Control for Tracking Bounded References With Arbitrary Dynamics
Cost function penalizes both artificial state error and reference error, while terminal constraint is imposed on artificial state error and artificial reference.
Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes
Feedforward neural networks are widely used in autonomous systems, particularly for control and perception tasks within the system loop.
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
Vision-language-action models (VLAs) show potential as generalist robot policies.
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC).
Soundwave: Less is More for Speech-Text Alignment in LLMs
Existing end-to-end speech large language models (LLMs) usually rely on large-scale annotated data for training, while data-efficient training has not been discussed in depth.
SegX: Improving Interpretability of Clinical Image Diagnosis with Segmentation-based Enhancement
Deep learning-based medical image analysis faces a significant barrier due to the lack of interpretability.
Optimizing Speech Multi-View Feature Fusion through Conditional Computation
Recent advancements have highlighted the efficacy of self-supervised learning (SSL) features in various speech-related tasks, providing lightweight and versatile multi-view speech representations.
Robust Model Predictive Control for Constrained Uncertain Systems Based on Concentric Container and Varying Tube
By restricting states and the corresponding inputs in containers with free sizes and a fixed shape, feasible MDs, which are the products of model uncertainty with states and inputs, are restricted into polytopes with free sizes.
Roadmap towards Superhuman Speech Understanding using Large Language Models
The success of large language models (LLMs) has prompted efforts to integrate speech and audio data, aiming to create general foundation models capable of processing both textual and non-textual inputs.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts.
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models
Surprisingly, we find that less is more, as training ReSet with high-quality, yet substantially smaller data (three-fold less) yields superior results.
RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
Question answering based on retrieval augmented generation (RAG-QA) is an important research topic in NLP and has a wide range of real-world applications.
NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU
However, these methods incur significant computational overhead as the camera tracking needs to wait for the deep neural network to generate mask at each frame, and they typically require GPUs for real-time operation, which restricts their practicality in real-world robotic applications.
CodeFort: Robust Training for Code Generation Models
Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models.
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models
Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values.
Verified Training for Counterfactual Explanation Robustness under Data Shift
Our empirical evaluation demonstrates that VeriTraCER generates CEs that (1) are verifiably robust to small model updates and (2) display competitive robustness to state-of-the-art approaches in handling empirical model updates including random initialization, leave-one-out, and distribution shifts.
Soft Alignment of Modality Space for End-to-end Speech Translation
End-to-end Speech Translation (ST) aims to convert speech into target text within a unified model.
DragVideo: Interactive Drag-style Video Editing
The main issues are: 1) how to perform direct and accurate user control in editing; 2) how to execute editings like changing shape, expression, and layout without unsightly distortion and artifacts to the edited content; and 3) how to maintain spatio-temporal consistency of video after editing.
Semantic-Aware Frame-Event Fusion based Pattern Recognition via Large Vision-Language Models
Current methods typically employ backbone networks to individually extract the features of RGB frames and event streams, and subsequently fuse these features for pattern recognition.
TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System
We anticipate that our work will contribute to the advancement of research on TrainerAgent in both academic and industry communities, potentially establishing it as a new paradigm for model development in the field of AI.
Rethinking and Improving Multi-task Learning for End-to-end Speech Translation
Significant improvements in end-to-end speech translation (ST) have been achieved through the application of multi-task learning.
Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition
In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and language in the speech translation (ST) task.
Channel sensing for holographic interference surfaces based on the principle of interferometry
In this paper, we derive the principles of holographic interference theory for electromagnetic wave reception and transmission, whereby the optical holography is extended to communication holography and a channel sensing architecture for holographic interference surfaces is established.
Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge.
CTC-based Non-autoregressive Speech Translation
Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation and low latency.
Bridging the Granularity Gap for Acoustic Modeling
While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights.
A multi-functional simulation platform for on-demand ride service operations
In addition, the existing simulators still face many challenges, ranging from their closeness to real environments of ride-sourcing systems, to the completeness of different tasks they can implement.
Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects
To assure high reliability against numerical defects, in this paper, we propose the RANUM approach including novel techniques for three reliability assurance tasks: detection of potential numerical defects, confirmation of potential-defect feasibility, and suggestion of defect fixes.
PECAN: A Deterministic Certified Defense Against Backdoor Attacks
Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the prediction of the victim model.
Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks
We show that, with consistent tokenization, the model performs better in both in-domain and out-of-domain datasets, with a notable average of +1. 7 F2 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets.
Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations
There has been great progress in unifying various table-to-text tasks using a single encoder-decoder model trained via multi-task learning (Xie et al., 2022).
Overwatch: Learning Patterns in Code Edit Sequences
Our experiments show that Overwatch has 78% precision and that Overwatch not only completed edits when developers missed the opportunity to use the IDE tool support but also predicted new edits that have no tool support in the IDE.
Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning
We introduce the initial release of our software Robustar, which aims to improve the robustness of vision classification machine learning models through a data-driven perspective.
Vertical GaN Diode BV Maximization through Rapid TCAD Simulation and ML-enabled Surrogate Model
In this paper, two methodologies are used to speed up the maximization of the breakdown volt-age (BV) of a vertical GaN diode that has a theoretical maximum BV of ~2100V.
An Ultra-low Power TinyML System for Real-time Visual Processing at Edge
Tiny machine learning (TinyML), executing AI workloads on resource and power strictly restricted systems, is an important and challenging topic.
BagFlip: A Certified Defense against Data Poisoning
Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model.
Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization
By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the state-of-the-art performance in terms of accuracy, latency and energy preservation.
RadGraph: Extracting Clinical Entities and Relations from Radiology Reports
We release a development dataset, which contains board-certified radiologist annotations for 500 radiology reports from the MIMIC-CXR dataset (14, 579 entities and 10, 889 relations), and a test dataset, which contains two independent sets of board-certified radiologist annotations for 100 radiology reports split equally across the MIMIC-CXR and CheXpert datasets.
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
To our knowledge, we are the first to develop an end-to-end ST system that achieves comparable or even better BLEU performance than the cascaded ST counterpart when large-scale ASR and MT data is available.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Brain Tumors Classification for MR images based on Attention Guided Deep Learning Model
In the clinical diagnosis and treatment of brain tumors, manual image reading consumes a lot of energy and time.
Certified Robustness to Programmable Transformations in LSTMs
Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction.
Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation
We further show via a human evaluation and a qualitative analysis that our system leads to generations that are more factually complete and consistent compared to the baselines.
Contrastive Learning of Medical Visual Representations from Paired Images and Text
Existing work commonly relies on fine-tuning weights transferred from ImageNet pretraining, which is suboptimal due to drastically different image characteristics, or rule-based label extraction from the textual report data paired with medical images, which is inaccurate and hard to generalize.
Do Syntax Trees Help Pre-trained Transformers Extract Information?
Our empirical analysis demonstrates that these syntax-infused transformers obtain state-of-the-art results on SRL and relation extraction tasks.
Biomedical and Clinical English Model Packages in the Stanza Python NLP Library
We introduce biomedical and clinical English model packages for the Stanza Python NLP library.
Learning Architectures from an Extended Search Space for Language Modeling
Neural architecture search (NAS) has advanced significantly in recent years but most NAS systems restrict search to learning architectures of a recurrent or convolutional cell.
Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations
We investigate the problem of generating informative questions in information-asymmetric conversations.
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages.
Ranked #1 on
Named Entity Recognition
on OntoNotes
Robustness to Programmable String Transformations via Augmented Abstract Training
We then present an approach to adversarially training models that are robust to such user-defined string transformations.
Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports
Neural abstractive summarization models are able to generate summaries which have high overlap with human references.
The NiuTrans Machine Translation Systems for WMT19
We participated in 13 translation directions, including 11 supervised tasks, namely EN↔{ZH, DE, RU, KK, LT}, GU→EN and the unsupervised DE↔CS sub-track.
Universal Dependency Parsing from Scratch
This paper describes Stanford's system at the CoNLL 2018 UD Shared Task.
Ranked #4 on
Dependency Parsing
on Universal Dependencies
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
Dependency trees help relation extraction models capture long-range relations between words.
Ranked #5 on
Relation Classification
on TACRED
Learning to Summarize Radiology Findings
The Impression section of a radiology report summarizes crucial radiology findings in natural language and plays a central role in communicating these findings to physicians.
MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
In particular, given a target model, our framework includes multiple models (constructed from the target model) to form a model family.
Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search
To our best knowledge, this paper presents the first substantial work tackling search over social media posts using neural ranking models.
Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning
Motivation: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases.
Position-aware Attention and Supervised Data Improve Slot Filling
The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance.
Ranked #7 on
Relation Extraction
on Re-TACRED
Segmental Convolutional Neural Networks for Detection of Cardiac Abnormality With Noisy Heart Sound Recordings
Heart diseases constitute a global health burden, and the problem is exacerbated by the error-prone nature of listening to and interpreting heart sounds.
Deep Convolutional Network for Handwritten Chinese Character Recognition
In this project we explored the performance of deep convolutional neural network on recognizing handwritten Chinese characters.
