no code implementations • 13 Mar 2024 • Yukun Ma, Zikun Mao
A large number of experimental results show that the proposed model can effectively detect the dynamic liquid level changes of the liquid in the container, providing a novel and efficient solution for related fields.
no code implementations • 4 Jan 2024 • Chen Zheng, Ke Sun, Da Tang, Yukun Ma, Yuyu Zhang, Chenguang Xi, Xun Zhou
The emergence of Large Language Models (LLMs) such as ChatGPT and LLaMA encounter limitations in domain-specific tasks, with these models often lacking depth and accuracy in specialized areas, and exhibiting a decrease in general capabilities when fine-tuned, particularly analysis ability in small sized models.
1 code implementation • 8 Nov 2023 • Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Shiliang Zhang, Chong Deng, Yukun Ma, Hai Yu, Jiaqing Liu, Chong Zhang
We find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over the Loss Masking approach.
no code implementations • 7 Oct 2023 • Zheng Zhang, Chen Zheng, Da Tang, Ke Sun, Yukun Ma, Yingtong Bu, Xun Zhou, Liang Zhao
This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks.
1 code implementation • 22 Sep 2023 • Jia Qi Yip, Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Dianwen Ng, Eng Siong Chng, Bin Ma
Dual-path is a popular architecture for speech separation models (e. g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships.
Ranked #5 on Speech Separation on WSJ0-2mix
1 code implementation • 20 May 2023 • Jia Qi Yip, Tuan Truong, Dianwen Ng, Chong Zhang, Yukun Ma, Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Eng Siong Chng, Bin Ma
In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetric Cross Attention (ACA) to replace temporal pooling.
1 code implementation • 18 May 2023 • Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Chong Deng, Hai Yu, Jiaqing Liu, Yukun Ma, Chong Zhang
Prior studies diagnose the anisotropy problem in sentence representations from pre-trained language models, e. g., BERT, without fine-tuning.
no code implementations • 18 Apr 2023 • Yukun Ma, Pedro H. C. Sant'Anna, Yuya Sasaki, Takuya Ura
In this paper, we derive a new class of doubly robust estimators for treatment effect estimands that is also robust against weak covariate overlap.
no code implementations • 7 Mar 2023 • Jinjie Ni, Yukun Ma, Wen Wang, Qian Chen, Dianwen Ng, Han Lei, Trung Hieu Nguyen, Chong Zhang, Bin Ma, Erik Cambria
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models.
no code implementations • 20 Feb 2023 • Yukun Ma
This paper presents an inference method for the local average treatment effect (LATE) in the presence of high-dimensional covariates, irrespective of the strength of identification.
no code implementations • 8 Oct 2021 • Harold D Chiang, Yukun Ma, Joel Rodrigue, Yuya Sasaki
Together with the use of Neyman orthogonal scores, this novel cross fitting method enables root-$n$ consistent estimation and inference robustly against dyadic dependence.
4 code implementations • ICLR 2021 • Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, Hongsheng Li
In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network, which can maintain the advantages of both unstructured fine-grained sparsity and structured coarse-grained sparsity simultaneously on specifically designed GPUs.
no code implementations • IJCNLP 2019 • Yukun Ma, Patrick H. Chen, Cho-Jui Hsieh
For example, input embedding and Softmax matrices in IWSLT-2014 German-to-English data set account for more than 80{\%} of the total model parameters.
1 code implementation • 15 Oct 2019 • Tianyu Li, Chien-Chih Wang, Yukun Ma, Patricia Ortal, Qifang Zhao, Bjorn Stenger, Yu Hirate
Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model.
no code implementations • 31 Aug 2019 • Zhuoran Yu, Aojun Zhou, Yukun Ma, Yudian Li, Xiaohan Zhang, Ping Luo
Experiment results show that SCT improves accuracy of single Resnet-50 on ImageNet by 1. 7% and 11. 5% accuracy when testing on image sizes of 224 and 128 respectively.
no code implementations • 23 Jan 2019 • Haiyun Peng, Yukun Ma, Soujanya Poria, Yang Li, Erik Cambria
Furthermore, we also fuse phonetic features with textual and visual features in order to mimic the way humans read and understand Chinese text.
no code implementations • 17 Dec 2018 • Tianyu Li, Yukun Ma, Jiu Xu, Bjorn Stenger, Chen Liu, Yu Hirate
This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems.
no code implementations • 15 Jul 2018 • Yukun Ma, Erik Cambria
In this work, we focus on effectively leveraging and integrating information from concept-level as well as word-level via projecting concepts and words into a lower dimensional space while retaining most critical semantics.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) 2018 • Yukun Ma, Haiyun Peng, Erik Cambria
Analyzing people’s opinions and sentiments towards certain aspects is an important task of natural language understanding.
Ranked #4 on Aspect-Based Sentiment Analysis (ABSA) on Sentihood
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3
no code implementations • COLING 2016 • Yukun Ma, Erik Cambria, Sa Gao
Named entity typing is the task of detecting the types of a named entity in context.