no code implementations • 29 Feb 2024 • Yuqiao Wen, Behzad Shayegh, Chenyang Huang, Yanshuai Cao, Lili Mou
The ability of zero-shot translation emerges when we train a multilingual model with certain translation directions; the model can then directly translate in unseen directions.
1 code implementation • 5 Feb 2024 • Yongchang Hao, Yanshuai Cao, Lili Mou
Despite large neural networks demonstrating remarkable abilities to complete different tasks, they require excessive memory usage to store the optimization states for training.
no code implementations • 5 Feb 2024 • Yongchang Hao, Yanshuai Cao, Lili Mou
The major reason is due to the quadratic memory and cubic time complexity to compute the inverse of the matrix.
1 code implementation • 3 Oct 2023 • Behzad Shayegh, Yanshuai Cao, Xiaodan Zhu, Jackie C. K. Cheung, Lili Mou
We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data.
2 code implementations • 29 Sep 2022 • Yuqiao Wen, Yongchang Hao, Yanshuai Cao, Lili Mou
Open-domain dialogue systems aim to interact with humans through natural language texts in an open-ended fashion.
no code implementations • 4 Dec 2021 • Wei Yang, Peng Xu, Yanshuai Cao
Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.
1 code implementation • ACL 2021 • Sajad Norouzi, Keyi Tang, Yanshuai Cao
Training datasets for semantic parsing are typically small due to the higher expertise required for annotation than most other NLP tasks.
no code implementations • ACL 2021 • Peng Xu, Wenjie Zi, Hamidreza Shahidi, Ákos Kádár, Keyi Tang, Wei Yang, Jawad Ateeq, Harsh Barot, Meidan Alon, Yanshuai Cao
A natural language database interface (NLDB) can democratize data-driven insights for non-technical users.
no code implementations • ACL (spnlp) 2021 • Chenyang Huang, Wei Yang, Yanshuai Cao, Osmar Zaïane, Lili Mou
In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing.
1 code implementation • 1 Jan 2021 • Sajad Norouzi, Keyi Tang, Yanshuai Cao
Training datasets for semantic parsing are typically small due to the higher expertise required for annotation than most other NLP tasks.
Ranked #2 on Code Generation on Django
1 code implementation • ACL 2021 • Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J. D. Prince, Yanshuai Cao
This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.
2 code implementations • ICML 2020 • Sicong Huang, Alireza Makhzani, Yanshuai Cao, Roger Grosse
The field of deep generative modeling has succeeded in producing astonishingly realistic-seeming images and audio, but quantitative evaluation remains a challenge.
no code implementations • 24 Feb 2020 • Ruizhi Deng, Yanshuai Cao, Bo Chang, Leonid Sigal, Greg Mori, Marcus A. Brubaker
In this work, we propose a novel probabilistic sequence model that excels at capturing high variability in time series data, both across sequences and within an individual sequence.
no code implementations • 10 Nov 2019 • Teng Long, Yanshuai Cao, Jackie Chi Kit Cheung
Variational autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic properties from local regularities of natural language.
1 code implementation • ICML 2020 • Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao
The variational autoencoder (VAE) can learn the manifold of natural images on certain datasets, as evidenced by meaningful interpolating or extrapolating in the continuous latent space.
1 code implementation • ACL 2019 • Peng Xu, Hamidreza Saghir, Jin Sung Kang, Teng Long, Avishek Joey Bose, Yanshuai Cao, Jackie Chi Kit Cheung
Coherence is an important aspect of text quality and is crucial for ensuring its readability.
1 code implementation • 28 May 2019 • Yanshuai Cao, Peng Xu
In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data.
no code implementations • 3 Dec 2018 • Junfeng Wen, Yanshuai Cao, Ruitong Huang
We demonstrate the superiority of our method to the previous ones in two different continual learning settings on popular benchmarks, as well as a new continual learning problem where tasks are designed to be more dissimilar.
no code implementations • ACL 2018 • Avishek Joey Bose, Huan Ling, Yanshuai Cao
Learning by contrasting positive and negative samples is a general strategy adopted by many methods.
1 code implementation • ICLR 2018 • Yanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui, Ruitong Huang
We propose a novel regularizer to improve the training of Generative Adversarial Networks (GANs).
no code implementations • 30 Oct 2017 • Kry Yik Chau Lui, Yanshuai Cao, Maxime Gazeau, Kelvin Shuangjian Zhang
This paper raises an implicit manifold learning perspective in Generative Adversarial Networks (GANs), by studying how the support of the learned distribution, modelled as a submanifold $\mathcal{M}_{\theta}$, perfectly match with $\mathcal{M}_{r}$, the support of the real data distribution.
no code implementations • 10 Aug 2017 • Yanshuai Cao, Luyu Wang
t-Distributed Stochastic Neighbor Embedding (t-SNE) is one of the most widely used dimensionality reduction methods for data visualization, but it has a perplexity hyperparameter that requires manual selection.
no code implementations • 24 Nov 2015 • Yanshuai Cao, David J. Fleet
We introduce a framework for analyzing transductive combination of Gaussian process (GP) experts, where independently trained GP experts are combined in a way that depends on test point location, in order to scale GPs to big data.
2 code implementations • 16 Nov 2015 • Sara Sabour, Yanshuai Cao, Fartash Faghri, David J. Fleet
We show that the representation of an image in a deep neural network (DNN) can be manipulated to mimic those of other natural images, with only minor, imperceptible perturbations to the original image.
no code implementations • 28 Oct 2014 • Yanshuai Cao, David J. Fleet
In this work, we propose a generalized product of experts (gPoE) framework for combining the predictions of multiple probabilistic models.
no code implementations • NeurIPS 2013 • Yanshuai Cao, Marcus A. Brubaker, David J. Fleet, Aaron Hertzmann
We propose an efficient optimization algorithm for selecting a subset of training data to induce sparsity for Gaussian process regression.