no code implementations • EMNLP 2020 • Jiaji Huang, Xingyu Cai, Kenneth Church
This paper designs a Monolingual Lexicon Induction task and observes that two factors accompany the degraded accuracy of bilingual lexicon induction for rare words.
no code implementations • 12 Jul 2024 • Youngsuk Park, Kailash Budhathoki, Liangfu Chen, Jonas Kübler, Jiaji Huang, Matthäus Kleindessner, Jun Huan, Volkan Cevher, Yida Wang, George Karypis
Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries.
no code implementations • 27 Apr 2022 • Guangxu Xun, Mingbo Ma, Yuchen Bian, Xingyu Cai, Jiaji Huang, Renjie Zheng, Junkun Chen, Jiahong Yuan, Kenneth Church, Liang Huang
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.
1 code implementation • NeurIPS 2021 • Jiaji Huang, Qiang Qiu, Kenneth Church
We model the space of tasks as a Gaussian process.
no code implementations • ICLR 2022 • Xingyu Cai, Jiahong Yuan, Yuchen Bian, Guangxu Xun, Jiaji Huang, Kenneth Church
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
no code implementations • NAACL 2021 • Yuchen Bian, Jiaji Huang, Xingyu Cai, Jiahong Yuan, Kenneth Church
(What) We define and focus the study on redundancy matrices generated from pre-trained and fine-tuned BERT-base model for GLUE datasets.
no code implementations • 12 May 2021 • Boxiang Liu, Jiaji Huang, Xingyu Cai, Kenneth Church
This paper compares BERT-SQuAD and Ab3P on the Abbreviation Definition Identification (ADI) task.
no code implementations • ICLR 2021 • Xingyu Cai, Jiaji Huang, Yuchen Bian, Kenneth Church
We hope the study in this paper could provide insights towards a better understanding of the deep language models.
11 code implementations • ICLR 2021 • Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, Bryan Catanzaro
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation.
Ranked #2 on
Speech Synthesis
on LJSpeech
3 code implementations • ICCV 2021 • Sherif Abdelkarim, Aniket Agarwal, Panos Achlioptas, Jun Chen, Jiaji Huang, Boyang Li, Kenneth Church, Mohamed Elhoseiny
We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup.
1 code implementation • ACL 2019 • Jiaji Huang, Qiang Qiu, Kenneth Church
Recent advances in BLI work by aligning the two word embedding spaces.
no code implementations • 23 Oct 2018 • Mostofa Patwary, Milind Chabbi, Heewoo Jun, Jiaji Huang, Gregory Diamos, Kenneth Church
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.
no code implementations • EMNLP 2018 • Jiaji Huang, Yi Li, Wei Ping, Liang Huang
We propose a large margin criterion for training neural language models.
no code implementations • 28 Dec 2017 • Wenlin Wang, Zhe Gan, Wenqi Wang, Dinghan Shen, Jiaji Huang, Wei Ping, Sanjeev Satheesh, Lawrence Carin
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.
no code implementations • CVPR 2018 • Wei Zhu, Qiang Qiu, Jiaji Huang, Robert Calderbank, Guillermo Sapiro, Ingrid Daubechies
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.
no code implementations • 11 May 2017 • Eric Battenberg, Rewon Child, Adam Coates, Christopher Fougner, Yashesh Gaur, Jiaji Huang, Heewoo Jun, Ajay Kannan, Markus Kliegl, Atul Kumar, Hairong Liu, Vinay Rao, Sanjeev Satheesh, David Seetapun, Anuroop Sriram, Zhenyao Zhu
Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition.
no code implementations • 10 Dec 2016 • Jiaji Huang, Rewon Child, Vinay Rao, Hairong Liu, Sanjeev Satheesh, Adam Coates
For speech recognition, confidence scores and other likelihood-based active learning methods have been shown to be effective.
no code implementations • 21 Dec 2015 • Jiaji Huang, Qiang Qiu, Robert Calderbank, Guillermo Sapiro
The new method encourages the relationships between the learned decisions to resemble a graph representing the manifold structure.
no code implementations • NeurIPS 2015 • Jiaji Huang, Qiang Qiu, Guillermo Sapiro, Robert Calderbank
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.
no code implementations • ICCV 2015 • Jiaji Huang, Qiang Qiu, Robert Calderbank, Guillermo Sapiro
Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets.
no code implementations • 15 Jul 2015 • Jiaji Huang, Qiang Qiu, Robert Calderbank
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.