Search Results for author: Chunchuan Lyu

Found 7 papers, 4 papers with code

Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models

no code implementations11 Jun 2021 Jing Liu, Rupak Vignesh Swaminathan, Sree Hari Krishnan Parthasarathi, Chunchuan Lyu, Athanasios Mouchtaris, Siegfried Kunzmann

We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind.

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

no code implementations EMNLP 2021 Chunchuan Lyu, Shay B. Cohen, Ivan Titov

In contrast, we treat both alignment and segmentation as latent variables in our model and induce them as part of end-to-end training.

AMR Parsing

Nonparametric Learning of Two-Layer ReLU Residual Units

1 code implementation17 Aug 2020 Zhunxuan Wang, Linyun He, Chunchuan Lyu, Shay B. Cohen

We describe an algorithm that learns two-layer residual units using rectified linear unit (ReLU) activation: suppose the input $\mathbf{x}$ is from a distribution with support space $\mathbb{R}^d$ and the ground-truth generative model is a residual unit of this type, given by $\mathbf{y} = \boldsymbol{B}^\ast\left[\left(\boldsymbol{A}^\ast\mathbf{x}\right)^+ + \mathbf{x}\right]$, where ground-truth network parameters $\boldsymbol{A}^\ast \in \mathbb{R}^{d\times d}$ represent a full-rank matrix with nonnegative entries and $\boldsymbol{B}^\ast \in \mathbb{R}^{m\times d}$ is full-rank with $m \geq d$ and for $\boldsymbol{c} \in \mathbb{R}^d$, $[\boldsymbol{c}^{+}]_i = \max\{0, c_i\}$.

Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks

1 code implementation IJCNLP 2019 Xinchi Chen, Chunchuan Lyu, Ivan Titov

In every network layer, the capsules interact with each other and with representations of words in the sentence.

Semantic Role Labeling

Semantic Role Labeling with Iterative Structure Refinement

1 code implementation IJCNLP 2019 Chunchuan Lyu, Shay B. Cohen, Ivan Titov

Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on expressive sentence encoders (e. g., multi-layer LSTMs) but tend to model only local (if any) interactions between individual argument labeling decisions.

Semantic Role Labeling

AMR Parsing as Graph Prediction with Latent Alignment

2 code implementations ACL 2018 Chunchuan Lyu, Ivan Titov

AMR parsing is challenging partly due to the lack of annotated alignments between nodes in the graphs and words in the corresponding sentences.

AMR Parsing

A Unified Gradient Regularization Family for Adversarial Examples

no code implementations19 Nov 2015 Chunchuan Lyu, Kai-Zhu Huang, Hai-Ning Liang

In this paper, we propose a unified framework to build robust machine learning models against adversarial examples.

BIG-bench Machine Learning Data Augmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.