中文
相关论文

相关论文: Sequential Latent Spaces for Modeling the Intentio…

200 篇论文

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

机器学习 · 计算机科学 2016-11-07 Hyo-Eun Kim , Sangheum Hwang , Kyunghyun Cho

Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP). We want to learn a model that approximates the conditional latent space over the representations of a logical…

计算与语言 · 计算机科学 2018-03-08 Yikang Shen , Shawn Tan , Chin-Wei Huang , Aaron Courville

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the data generation, and improve the sample efficiency for…

机器学习 · 计算机科学 2021-10-26 Junwen Bai , Weiran Wang , Carla Gomes

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

计算与语言 · 计算机科学 2019-11-12 Zhuosheng Zhang , Rui Wang , Kehai Chen , Masao Utiyama , Eiichiro Sumita , Hai Zhao

Sequential modelling of high-dimensional data is an important problem that appears in many domains including model-based reinforcement learning and dynamics identification for control. Latent variable models applied to sequential data…

机器学习 · 计算机科学 2023-01-23 Oliver Limoyo , Trevor Ablett , Jonathan Kelly

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the…

机器学习 · 计算机科学 2019-12-02 Le Fang , Chunyuan Li , Jianfeng Gao , Wen Dong , Changyou Chen

Structuring the latent space in probabilistic deep generative models, e.g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting. One way to achieve this…

机器学习 · 计算机科学 2022-06-20 Mostafa Sadeghi , Paul Magron

We present an unsupervised method to obtain disentangled representations of sentences that single out semantic content. Using modified Transformers as building blocks, we train a Variational Autoencoder to translate the sentence to a fixed…

计算与语言 · 计算机科学 2020-12-29 Ghazi Felhi , Joseph Le Roux , Djamé Seddah

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

计算与语言 · 计算机科学 2026-03-24 Lorenzo Noci , Gregor Bachmann , Seyed-Mohsen Moosavi-Dezfooli , Moin Nabi

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

机器学习 · 计算机科学 2018-12-18 Jack Klys , Jake Snell , Richard Zemel

We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences. Distinct from existing VAE-based text generative models, SIVAE contains two…

机器学习 · 统计学 2019-06-11 Xinyuan Zhang , Yi Yang , Siyang Yuan , Dinghan Shen , Lawrence Carin

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…

计算与语言 · 计算机科学 2017-11-23 Dinghan Shen , Yizhe Zhang , Ricardo Henao , Qinliang Su , Lawrence Carin

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

计算与语言 · 计算机科学 2022-10-28 Liliang Ren , Zixuan Zhang , Han Wang , Clare R. Voss , Chengxiang Zhai , Heng Ji

In this work we explore deep generative models of text in which the latent representation of a document is itself drawn from a discrete language model distribution. We formulate a variational auto-encoder for inference in this model and…

计算与语言 · 计算机科学 2016-10-17 Yishu Miao , Phil Blunsom

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

机器学习 · 计算机科学 2025-08-05 Theodoros Kouzelis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

Data scarcity is one of the main obstacles of domain adaptation in spoken language understanding (SLU) due to the high cost of creating manually tagged SLU datasets. Recent works in neural text generative models, particularly latent…

计算与语言 · 计算机科学 2018-11-07 Kang Min Yoo , Youhyun Shin , Sang-goo Lee

We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative labeler. The generative models use latent variables to define…

计算与语言 · 计算机科学 2019-06-25 Mingda Chen , Qingming Tang , Karen Livescu , Kevin Gimpel

Extracting time-varying latent variables from computational cognitive models is a key step in model-based neural analysis, which aims to understand the neural correlates of cognitive processes. However, existing methods only allow…

机器学习 · 计算机科学 2025-09-01 Ti-Fen Pan , Jing-Jing Li , Bill Thompson , Anne Collins

Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs) have contributed a highly effective adversarial learning…

计算机视觉与模式识别 · 计算机科学 2018-08-14 Yang He , Bernt Schiele , Mario Fritz

Semantic image synthesis is a process for generating photorealistic images from a single semantic mask. To enrich the diversity of multimodal image synthesis, previous methods have controlled the global appearance of an output image by…

计算机视觉与模式识别 · 计算机科学 2021-06-30 Yuki Endo , Yoshihiro Kanamori