Search Results for author:
Found 49 papers, 15 papers with code
Conundrums in Event Coreference Resolution: Making Sense of the State of the Art
Despite recent promising results on the application of span-based models for event reference interpretation, there is a lack of understanding of what has been improved.
Multi-stage Training with Improved Negative Contrast for Neural Passage Retrieval
In the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion.
Conundrums in Entity Coreference Resolution: Making Sense of the State of the Art
Despite the significant progress on entity coreference resolution observed in recent years, there is a general lack of understanding of what has been improved.
Active headrest combined with a depth camera-based ear-positioning system
Active headrests can reduce low-frequency noise around ears based on active noise control (ANC) system.
LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
Through meta-learning techniques, LabelCraft effectively addresses the bi-level optimization hurdle posed by the recommender and labeling models, enabling the automatic acquisition of intricate label generation mechanisms. Extensive experiments on real-world datasets corroborate LabelCraft's excellence across varied operational metrics, encompassing usage time, user engagement, and retention.
Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
With the proliferation of short video applications, the significance of short video recommendations has vastly increased.
Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model
With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models.
Personalized speech enhancement combining band-split RNN and speaker attentive module
Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech.
TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou
And for the user-item cross features, we compress each into a one-dimentional bias term in the attention score calculation to save the computational cost.
Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation
While knowledge distillation, a prevailing technique in CIL, can alleviate the catastrophic forgetting of older classes by regularizing outputs between current and previous model, it fails to consider the overfitting risk of novel classes in FSCIL.
HyperMatch: Noise-Tolerant Semi-Supervised Learning via Relaxed Contrastive Constraint
Recent developments of the application of Contrastive Learning in Semi-Supervised Learning (SSL) have demonstrated significant advancements, as a result of its exceptional ability to learn class-aware cluster representations and the full exploitation of massive unlabeled data.
Distributed Active Noise Control System Based on a Block Diffusion FxLMS Algorithm with Bidirectional Communication
Recently, distributed active noise control systems based on diffusion adaptation have attracted significant research interest due to their balance between computational complexity and stability compared to conventional centralized and decentralized adaptation schemes.
HYRR: Hybrid Infused Reranking for Passage Retrieval
We present Hybrid Infused Reranking for Passages Retrieval (HYRR), a framework for training rerankers based on a hybrid of BM25 and neural retrieval models.
Distilling Object Detectors With Global Knowledge
Then, a robust distilling module (RDM) is applied to construct the global knowledge based on the prototypes and filtrate noisy global and local knowledge by measuring the discrepancy of the representations in two feature spaces.
RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses
Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT.
Promptagator: Few-shot Dense Retrieval From 8 Examples
To amplify the power of a few examples, we propose Prompt-base Query Generation for Retriever (Promptagator), which leverages large language models (LLM) as a few-shot query generator, and creates task-specific retrievers based on the generated data.
Rapid-Flooding Time Synchronization for Large-Scale Wireless Sensor Networks
Accurate and fast-convergent time synchronization is very important for wireless sensor networks.
Semi-blind source separation using convolutive transfer function for nonlinear acoustic echo cancellation
The recently proposed semi-blind source separation (SBSS) method for nonlinear acoustic echo cancellation (NAEC) outperforms adaptive NAEC in attenuating the nonlinear acoustic echo.
A light-weight full-band speech enhancement model
Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution.
ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference
This results in significant inference time speedups since the decoder-only architecture only needs to learn to interpret static encoder embeddings during inference.
PMAL: Open Set Recognition via Robust Prototype Mining
Accordingly, the embedding space can be better optimized to discriminate therein the predefined classes and between known and unknowns.
Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models
In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting.
Large Dual Encoders Are Generalizable Retrievers
With multi-stage training, surprisingly, scaling up the model size brings significant improvement on a variety of retrieval tasks, especially for out-of-domain generalization.
Ranked #9 on
Zero-shot Text Search
on BEIR
ICDAR 2021 Competition on Scene Video Text Spotting
During the competition period (opened on 1st March, 2021 and closed on 11th April, 2021), a total of 24 teams participated in the three proposed tasks with 46 valid submissions, respectively.
Constrained Multi-Task Learning for Event Coreference Resolution
We propose a neural event coreference model in which event coreference is jointly trained with five tasks: trigger detection, entity coreference, anaphoricity determination, realis detection, and argument extraction.
Coronary Plaque Analysis for CT Angiography Clinical Research
However, to enable clinical research with the help of these algorithms, a software solution, which enables manual correction, comprehensive visual feedback and tissue analysis capabilities, is needed.
Event Coreference Resolution with Non-Local Information
We present two extensions to a state-of-theart joint model for event coreference resolution, which involve incorporating (1) a supervised topic model for improving trigger detection by providing global context, and (2) a preprocessing module that seeks to improve event coreference by discarding unlikely candidate antecedents of an event mention using discourse contexts computed based on salient entities.
A Permissioned Blockchain-Based Platform for Education Certificate Verification
Distance education has become an important learning method for students.
Semi-Blind Source Separation for Nonlinear Acoustic Echo Cancellation
Unlike the commonly utilized adaptive algorithm, the proposed SBSS is based on the independence between the near-end signal and the reference signals, and is less sensitive to the mismatch of nonlinearity between the numerical and actual models.
Neural Passage Retrieval with Improved Negative Contrast
In this paper we explore the effects of negative sampling in dual encoder models used to retrieve passages for automatic question answering.
Kalman Filtering Attention for User Behavior Modeling in CTR Prediction
First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors.
improving partition-block-based acoustic echo canceler in under-modeling scenarios
Recently, a partitioned-block-based frequency-domain Kalman filter (PFKF) has been proposed for acoustic echo cancellation.
Category-Specific CNN for Visual-aware CTR Prediction at JD.com
Existing algorithms usually extract visual features using off-the-shelf Convolutional Neural Networks (CNNs) and late fuse the visual and non-visual features for the finally predicted CTR.
Object-QA: Towards High Reliable Object Quality Assessment
In this paper, we define the problem of object quality assessment for the first time and propose an effective approach named Object-QA to assess high-reliable quality scores for object images.
TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
Since real-world ubiquitous documents (e. g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic.
Target Speech Extraction Based on Blind Source Separation and X-vector-based Speaker Selection Trained with Data Augmentation
Extracting the desired speech from a mixture is a meaningful and challenging task.
Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet
Acoustic echo cannot be entirely removed by linear adaptive filters due to the nonlinear relationship between the echo and far-end signal.
Sampling Wisely: Deep Image Embedding by Top-K Precision Optimization
Consequently, gradient descent direction on the training loss is mostly inconsistent with the direction of optimizing the concerned evaluation metric.
Position Focused Attention Network for Image-Text Matching
Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence.
Improving Event Coreference Resolution by Learning Argument Compatibility from Unlabeled Data
Argument compatibility is a linguistic condition that is frequently incorporated into modern event coreference resolution systems.
You Only Recognize Once: Towards Fast Video Text Spotting
Video text spotting is still an important research topic due to its various real-applications.
Online Learning: A Comprehensive Survey
Online learning represents an important family of machine learning algorithms, in which a learner attempts to resolve an online prediction (or any type of decision-making) task by learning a model/hypothesis from a sequence of data instances one at a time.
Online Deep Learning: Learning Deep Neural Networks on the Fly
Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch learning setting, which requires the entire training data to be made available prior to the learning task.
Joint Learning for Event Coreference Resolution
While joint models have been developed for many NLP tasks, the vast majority of event coreference resolvers, including the top-performing resolvers competing in the recent TAC KBP 2016 Event Nugget Detection and Coreference task, are pipeline-based, where the propagation of errors from the trigger detection component to the event coreference component is a major performance limiting factor.
Joint Inference for Event Coreference Resolution
Event coreference resolution is a challenging problem since it relies on several components of the information extraction pipeline that typically yield noisy outputs.
SOL: A Library for Scalable Online Learning Algorithms
SOL is an open-source library for scalable online learning algorithms, and is particularly suitable for learning with high-dimensional data.
Event Coreference Resolution with Multi-Pass Sieves
Multi-pass sieve approaches have been successfully applied to entity coreference resolution and many other tasks in natural language processing (NLP), owing in part to the ease of designing high-precision rules for these tasks.
Detection and Visualization of Endoleaks in CT Data for Monitoring of Thoracic and Abdominal Aortic Aneurysm Stents
The aneurysm segmentation includes two steps: first, the inner boundary is segmented based on a grey level model with two thresholds; then, an adapted active contour model approach is applied to the more complicated outer boundary segmentation, with its initialization based on the available inner boundary segmentation.
Budget Online Multiple Kernel Learning
To overcome this drawback, we present a novel framework of Budget Online Multiple Kernel Learning (BOMKL) and propose a new Sparse Passive Aggressive learning to perform effective budget online learning.
