English
Related papers

Related papers: Multinomial Loss on Held-out Data for the Sparse N…

200 papers

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

Computation and Language · Computer Science 2022-10-28 Liliang Ren , Zixuan Zhang , Han Wang , Clare R. Voss , Chengxiang Zhai , Heng Ji

Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining. While methods exist to improve performance for unseen languages, they have almost exclusively…

Computation and Language · Computer Science 2021-06-07 Abteen Ebrahimi , Katharina Kann

Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning. However, their performance can be hampered by inherent biases. Instead of traditionally sought methods that aim…

Computation and Language · Computer Science 2024-01-19 Yong Zhang , Hanzhang Li , Zhitao Li , Ning Cheng , Ming Li , Jing Xiao , Jianzong Wang

Existing Speech Language Model (SLM) scaling analysis paints a bleak picture. It predicts that SLMs require much more compute and data compared to text, leading some to question the feasibility of training high-quality SLMs. However, modern…

Computation and Language · Computer Science 2025-07-29 Gallil Maimon , Michael Hassid , Amit Roth , Yossi Adi

We propose BlackOut, an approximation algorithm to efficiently train massive recurrent neural network language models (RNNLMs) with million word vocabularies. BlackOut is motivated by using a discriminative loss, and we describe a new…

Machine Learning · Computer Science 2016-04-01 Shihao Ji , S. V. N. Vishwanathan , Nadathur Satish , Michael J. Anderson , Pradeep Dubey

The application of loss reweighting in modern deep learning presents a nuanced picture. While it fails to alter the terminal learning phase in overparameterized deep neural networks (DNNs) trained on high-dimensional datasets, empirical…

Machine Learning · Computer Science 2026-01-21 Yize Zhao , Christos Thrampoulidis

Long Short-Term Memory (LSTM) has achieved state-of-the-art performances on a wide range of tasks. Its outstanding performance is guaranteed by the long-term memory ability which matches the sequential data perfectly and the gating…

Neural and Evolutionary Computing · Computer Science 2019-01-29 Shiwei Liu , Decebal Constantin Mocanu , Mykola Pechenizkiy

Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs…

Computation and Language · Computer Science 2024-06-07 Da Ma , Lu Chen , Pengyu Wang , Hongshen Xu , Hanqi Li , Liangtai Sun , Su Zhu , Shuai Fan , Kai Yu

Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel…

Computation and Language · Computer Science 2024-02-19 Dheeraj Mekala , Alex Nguyen , Jingbo Shang

Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other…

Computation and Language · Computer Science 2024-06-17 Jari Kolehmainen , Aditya Gourav , Prashanth Gurunath Shivakumar , Yile Gu , Ankur Gandhe , Ariya Rastrow , Grant Strimel , Ivan Bulyko

Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition…

Computation and Language · Computer Science 2017-09-07 Pranay Dighe , Afsaneh Asaei , Herve Bourlard

Speech separation remains an important area of multi-speaker signal processing. Deep neural network (DNN) models have attained the best performance on many speech separation benchmarks. Some of these models can take significant time to…

Sound · Computer Science 2023-06-19 William Ravenscroft , Stefan Goetze , Thomas Hain

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-01 Siyuan Feng , Tan Lee

Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine…

Computation and Language · Computer Science 2024-10-04 Minseok Choi , Kyunghyun Min , Jaegul Choo

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…

Computation and Language · Computer Science 2021-09-06 Yingmei Guo , Linjun Shou , Jian Pei , Ming Gong , Mingxing Xu , Zhiyong Wu , Daxin Jiang

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

Computation and Language · Computer Science 2021-06-11 Christos Baziotis , Ivan Titov , Alexandra Birch , Barry Haddow

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Computation and Language · Computer Science 2022-08-30 Boyang Xue , Shoukang Hu , Junhao Xu , Mengzhe Geng , Xunying Liu , Helen Meng

Target speech separation is the process of filtering a certain speaker's voice out of speech mixtures according to the additional speaker identity information provided. Recent works have made considerable improvement by processing signals…

Sound · Computer Science 2021-09-28 Qingjian Lin , Lin Yang , Xuyang Wang , Luyuan Xie , Chen Jia , Junjie Wang

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…

Computation and Language · Computer Science 2021-10-05 Yiming Chen , Yan Zhang , Chen Zhang , Grandee Lee , Ran Cheng , Haizhou Li

This paper proposes a fast and accurate method for sparse regression in the presence of missing data. The underlying statistical model encapsulates the low-dimensional structure of the incomplete data matrix and the sparsity of the…

Machine Learning · Statistics 2015-03-31 Ravi Ganti , Rebecca M. Willett