Search Results for author:
Found 20 papers, 4 papers with code
Improving Bilingual Lexicon Induction for Low Frequency Words
This paper designs a Monolingual Lexicon Induction task and observes that two factors accompany the degraded accuracy of bilingual lexicon induction for rare words.
Data-Driven Adaptive Simultaneous Machine Translation
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency.
W-CTC: a Connectionist Temporal Classification Loss with Wild Cards
Standard CTC computes a loss by aggregating over all possible alignment paths, that map the entire sequence to the entire label (full alignment).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
On Attention Redundancy: A Comprehensive Study
(What) We define and focus the study on redundancy matrices generated from pre-trained and fine-tuned BERT-base model for GLUE datasets.
Better than BERT but Worse than Baseline
This paper compares BERT-SQuAD and Ab3P on the Abbreviation Definition Identification (ADI) task.
Isotropy in the Contextual Embedding Space: Clusters and Manifolds
We hope the study in this paper could provide insights towards a better understanding of the deep language models.
DiffWave: A Versatile Diffusion Model for Audio Synthesis
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation.
Ranked #2 on
Speech Synthesis
on LJSpeech
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup.
Hubless Nearest Neighbor Search for Bilingual Lexicon Induction
Recent advances in BLI work by aligning the two word embedding spaces.
Language Modeling at Scale
We show how Zipf's Law can be used to scale up language modeling (LM) to take advantage of more training data and more GPUs.
Large Margin Neural Language Model
We propose a large margin criterion for training neural language models.
Topic Compositional Neural Language Model
The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence.
LDMNet: Low Dimensional Manifold Regularized Neural Networks
To resolve this, we propose a new framework, the Low-Dimensional-Manifold-regularized neural Network (LDMNet), which incorporates a feature regularization method that focuses on the geometry of both the input data and the output features.
Reducing Bias in Production Speech Models
Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition.
Active Learning for Speech Recognition: the Power of Gradients
For speech recognition, confidence scores and other likelihood-based active learning methods have been shown to be effective.
GraphConnect: A Regularization Framework for Neural Networks
The new method encourages the relationships between the learned decisions to resemble a graph representing the manifold structure.
Discriminative Robust Transformation Learning
This paper proposes a framework for learning features that are robust to data variation, which is particularly important when only a limited number of trainingsamples are available.
Geometry-aware Deep Transform
Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets.
The Role of Principal Angles in Subspace Classification
Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misclassification.
