Search Results for author:
Found 34 papers, 8 papers with code
S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
To this end, based on a given CNN model, we first generate a CNN architecture space in which each architecture is a multi-stage CNN generated from the given model using some predefined transformations.
Language Resource Efficient Learning for Captioning
Our analysis of caption models with SC loss shows that the performance degradation is caused by the increasingly noisy estimation of reward and baseline with fewer language resources.
DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency
As text-based speech editing becomes increasingly prevalent, the demand for unrestricted free-text editing continues to grow.
Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs).
Uncertainty-Aware Mean Opinion Score Prediction
Mean Opinion Score (MOS) prediction has made significant progress in specific domains.
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives
This paper introduces the Re-TASK framework, a novel theoretical model that revisits LLM tasks from the perspectives of capability, skill, and knowledge, drawing on the principles of Bloom's Taxonomy and Knowledge Space Theory.
Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptation
To address this issue, we introduce a prototype-based approach that markedly improves DSR performance for unseen dysarthric speakers without additional fine-tuning.
Enhancing Emotion Recognition in Incomplete Data: A Novel Cross-Modal Alignment, Reconstruction, and Refinement Framework
Multimodal emotion recognition systems rely heavily on the full availability of modalities, suffering significant performance declines when modal data is incomplete.
Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs
Consequently, the self-prompt tuned LLMs can automatically generate expert role prompts for any given question.
Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores
To address this, we propose a novel kNN-CTC-based code-switching ASR (CS-ASR) framework that employs dual monolingual datastores and a gated datastore selection mechanism to reduce noise interference.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Supervised Contrastive Learning with Nearest Neighbor Search for Speech Emotion Recognition
This approach increases the inter-class distances and decreases the intra-class distances, mitigating the issue of blurred boundaries.
Better Zero-Shot Reasoning with Role-Play Prompting
This highlights its potential to augment the reasoning capabilities of LLMs.
Uncertainty in Natural Language Processing: Sources, Quantification, and Applications
Therefore, in this survey, we provide a comprehensive review of uncertainty-relevant works in the NLP field.
Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction
We further propose marginalized unlikelihood learning to suppress the uncertainty-aware mistake tokens.
E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition
Most named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty, which is critical to the reliability of NER systems in open environments.
PromptRank: Unsupervised Keyphrase Extraction Using Prompt
This demonstrates the great potential of using prompt for unsupervised keyphrase extraction.
Ranked #1 on
Keyphrase Extraction
on NUS
MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition
Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain by transferring knowledge from the source to the target domain.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation
By fine-tuning the pre-trained language model with these template orders, our approach improves the performance of quad prediction, and outperforms state-of-the-art methods significantly in low-resource settings.
Ranked #3 on
Aspect-Based Sentiment Analysis (ABSA)
on ACOS
Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances
In this work, we define the training instances with the same question type but different answers as \textit{superficially similar instances}, and attribute the language priors to the confusion of VQA model on such instances.
Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement
A mind-map is a diagram that represents the central concept and key ideas in a hierarchical way.
Multi-Label Few-Shot Learning for Aspect Category Detection
Aspect category detection (ACD) in sentiment analysis aims to identify the aspect categories mentioned in a sentence.
Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning
In real world applications like healthcare, it is usually difficult to build a machine learning prediction model that works universally well across different institutions.
S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN).
Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent.
Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis
The attention is expected to concentrate on opinion words for accurate sentiment prediction.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification
Cross-domain sentiment classification has drawn much attention in recent years.
Improving Captioning for Low-Resource Languages by Cycle Consistency
Improving the captioning performance on low-resource languages by leveraging English caption datasets has received increasing research interest in recent years.
Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection.
P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification
(2) privacy leakage: the model trained using a conventional method may involuntarily reveal the private information of the patients in the training dataset.
CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis
Aspect level sentiment classification is a fine-grained sentiment analysis task.
Deep Diabetologist: Learning to Prescribe Hyperglycemia Medications with Hierarchical Recurrent Neural Networks
In healthcare, applying deep learning models to electronic health records (EHRs) has drawn considerable attention.
Infinite Curriculum Learning for Efficiently Detecting Gastric Ulcers in WCE Images
This paper considers WCE-based gastric ulcer detection, in which the major challenge is to detect the lesions in a local region.
G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification
Given an input image from a specified stain, several generators are first applied to estimate its appearances in other staining methods, and a classifier follows to combine visual cues from different stains for prediction (whether it is pathological, or which type of pathology it has).
