中文
相关论文

相关论文: Disentangled VAD Representations via a Variational…

200 篇论文

Stance detection is an important task, supporting many downstream tasks such as discourse parsing and modeling the propagation of fake news, rumors, and science denial. In this paper, we propose a novel framework for stance detection. Our…

计算与语言 · 计算机科学 2021-12-21 Ron Korenblum Pick , Vladyslav Kozhukhov , Dan Vilenchik , Oren Tsur

Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn…

机器学习 · 计算机科学 2026-01-13 Ioannis Ziogas , Aamna Al Shehhi , Ahsan H. Khandoker , Leontios J. Hadjileontiadis

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations…

计算与语言 · 计算机科学 2026-04-24 Hieu Man , Van-Cuong Pham , Nghia Trung Ngo , Franck Dernoncourt , Thien Huu Nguyen

A fully disentangled variational auto-encoder (VAE) aims to identify disentangled latent components from observations. However, enforcing full independence between all latent components may be too strict for certain datasets. In some cases,…

机器学习 · 计算机科学 2025-02-05 Chengrui Li , Yunmiao Wang , Yule Wang , Weihan Li , Dieter Jaeger , Anqi Wu

The ability to recognize objects despite there being differences in appearance, known as Core Object Recognition, forms a critical part of human perception. While it is understood that the brain accomplishes Core Object Recognition through…

机器学习 · 计算机科学 2020-05-15 Harshvardhan Sikka

Stance detection plays a pivotal role in enabling an extensive range of downstream applications, from discourse parsing to tracing the spread of fake news and the denial of scientific facts. While most stance classification models rely on…

计算与语言 · 计算机科学 2024-12-13 Guy Barel , Oren Tsur , Dan Vilenchik

Learning disentangled representations without supervision or inductive biases, often leads to non-interpretable or undesirable representations. On the other hand, strict supervision requires detailed knowledge of the true generative…

机器学习 · 计算机科学 2020-08-25 Vasilis Margonis , Athanasios Davvetas , Iraklis A. Klampanos

The rapid evolution of social media has generated an overwhelming volume of user-generated content, conveying implicit opinions and contributing to the spread of misinformation. The method aims to enhance the detection of stance where…

计算与语言 · 计算机科学 2025-06-02 Lata Pangtey , Mohammad Zia Ur Rehman , Prasad Chaudhari , Shubhi Bansal , Nagendra Kumar

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective…

声音 · 计算机科学 2020-07-29 Siddique Latif , Rajib Rana , Junaid Qadir , Julien Epps

A large part of the literature on learning disentangled representations focuses on variational autoencoders (VAE). Recent developments demonstrate that disentanglement cannot be obtained in a fully unsupervised setting without inductive…

机器学习 · 计算机科学 2021-02-11 Graziano Mita , Maurizio Filippone , Pietro Michiardi

Stance detection seeks to identify the viewpoints of individuals either in favor or against a given target or a controversial topic. Current advanced neural models for stance detection typically employ fully parametric softmax classifiers.…

机器学习 · 计算机科学 2024-06-21 Yinghan Cheng , Qi Zhang , Chongyang Shi , Liang Xiao , Shufeng Hao , Liang Hu

In modern digital environments, users frequently express opinions on contentious topics, providing a wealth of information on prevailing attitudes. The systematic analysis of these opinions offers valuable insights for decision-making in…

计算与语言 · 计算机科学 2024-11-26 Bowen Zhang , Genan Dai , Fuqiang Niu , Nan Yin , Xiaomao Fan , Senzhang Wang , Xiaochun Cao , Hu Huang

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a…

机器学习 · 计算机科学 2019-04-19 Mhd Hasan Sarhan , Abouzar Eslami , Nassir Navab , Shadi Albarqouni

Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a…

机器学习 · 计算机科学 2021-01-20 Jun Han , Martin Renqiang Min , Ligong Han , Li Erran Li , Xuan Zhang

Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost…

机器学习 · 统计学 2019-09-12 Jan Stühmer , Richard E. Turner , Sebastian Nowozin

Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning.…

机器学习 · 计算机科学 2018-12-04 Yang Li , Quan Pan , Suhang Wang , Haiyun Peng , Tao Yang , Erik Cambria

Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning…

In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others. If data generating factors are also statistically independent, disentangled…

机器学习 · 统计学 2019-12-12 Harshvardhan Sikka , Weishun Zhong , Jun Yin , Cengiz Pehlevan

An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this…

音频与语音处理 · 电气工程与系统科学 2020-04-09 Wen-Chin Huang , Hao Luo , Hsin-Te Hwang , Chen-Chou Lo , Yu-Huai Peng , Yu Tsao , Hsin-Min Wang

Evaluating and interpreting latent representations, such as variational autoencoders (VAEs), remains a significant challenge for diverse data types, especially when ground-truth generative factors are unknown. To address this, we propose a…

机器学习 · 统计学 2026-03-13 Xiaoan Lang , Fang Liu