English
Related papers

Related papers: Von Mises-Fisher Loss for Training Sequence to Seq…

200 papers

In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks. We focus on a broad class of ERM-based linear algorithms that can…

Machine Learning · Computer Science 2016-10-19 Ilja Kuzborskij , Francesco Orabona

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

Computation and Language · Computer Science 2024-05-31 Zhuoyuan Mao , Chenhui Chu , Sadao Kurohashi

Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly…

Machine Learning · Computer Science 2025-08-05 Jialiang Wang , Xiong Zhou , Deming Zhai , Junjun Jiang , Xiangyang Ji , Xianming Liu

Diffusion models have demonstrated strong potential in language modeling, offering various advantages over traditional autoregressive approaches. Their ability to generate and revise entire responses in parallel enables faster generation…

Machine Learning · Computer Science 2026-03-03 Michael Hersche , Samuel Moor-Smith , Thomas Hofmann , Abbas Rahimi

Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…

Computation and Language · Computer Science 2021-03-23 Chen Liang , Haoming Jiang , Xiaodong Liu , Pengcheng He , Weizhu Chen , Jianfeng Gao , Tuo Zhao

Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from…

Computation and Language · Computer Science 2018-10-18 Xuanli He , Gholamreza Haffari , Mohammad Norouzi

Diffusion language models have emerged as a promising approach for text generation. One would naturally expect this method to be an efficient replacement for autoregressive models since multiple tokens can be sampled in parallel during each…

Machine Learning · Computer Science 2025-06-10 Guhao Feng , Yihan Geng , Jian Guan , Wei Wu , Liwei Wang , Di He

Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune these models on…

Computation and Language · Computer Science 2021-07-22 Weijia Xu , Batool Haider , Jason Krone , Saab Mansour

Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-07 Yassir Fathullah , Chao Zhang , Philip C. Woodland

Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their extensive output vocabularies. The final linear projection layer, mapping hidden states to…

Computation and Language · Computer Science 2025-05-16 Jintian Shao , Hongyi Huang , Jiayi Wu , YiMing Cheng , ZhiYu Wu , You Shan , MingKai Zheng

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

The last layer of neural language models (LMs) projects output features of dimension $D$ to logits in dimension $V$, the size of the vocabulary, where usually $D \ll V$. This mismatch is known to raise risks of limited expressivity in…

Computation and Language · Computer Science 2026-03-12 Nathan Godey , Yoav Artzi

There have been significant advancements made by large language models (LLMs) in various aspects of our daily lives. LLMs serve as a transformative force in natural language processing, finding applications in text generation, translation,…

Machine Learning · Computer Science 2023-11-28 Zhihang Li , Zhao Song , Zifan Wang , Junze Yin

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance…

Computation and Language · Computer Science 2024-12-16 Daniele Rege Cambrin , Giuseppe Gallipoli , Irene Benedetto , Luca Cagliero , Paolo Garza

Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial. Previous works utilize linear interpolation or a fusion network to integrate external language models. However, these approaches…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-16 Ye Bai , Jiangyan Yi , Jianhua Tao , Zhengkun Tian , Zhengqi Wen

In text generation, a large language model (LM) makes a choice of each new word based only on the former selection of its context using the softmax function. Nevertheless, the link statistics information of concurrent words based on a…

Computation and Language · Computer Science 2023-12-20 Liu Bin , Yin Guosheng

Training large language models (LLMs) is computationally expensive, partly because the loss exhibits slow power-law convergence whose origin remains debatable. Through systematic analysis of toy models and empirical evaluation of LLMs, we…

Machine Learning · Computer Science 2026-02-04 Yizhou Liu , Ziming Liu , Cengiz Pehlevan , Jeff Gore

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse…

Machine Learning · Computer Science 2019-07-04 Shun Liao , Ting Chen , Tian Lin , Denny Zhou , Chong Wang

We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound…

Machine Learning · Computer Science 2024-01-10 Shehzaad Dhuliawala , Mrinmaya Sachan , Carl Allen
‹ Prev 1 4 5 6 7 8 10 Next ›