English
Related papers

Related papers: Breaking the Softmax Bottleneck: A High-Rank RNN L…

200 papers

Training neural network language models over large vocabularies is still computationally very costly compared to count-based models such as Kneser-Ney. At the same time, neural language models are gaining popularity for many applications…

Computation and Language · Computer Science 2015-12-16 Welin Chen , David Grangier , Michael Auli

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable…

Computation and Language · Computer Science 2024-07-10 Nan He , Weichen Xiong , Hanwen Liu , Yi Liao , Lei Ding , Kai Zhang , Guohua Tang , Xiao Han , Wei Yang

In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of…

Computation and Language · Computer Science 2018-03-15 Jacob Buckman , Graham Neubig

Augmenting a language model (LM) with $k$-nearest neighbors ($k$NN) retrieval on its training data alone can decrease its perplexity, though the underlying reasons for this remain elusive. In this work, we rule out one previously posited…

Computation and Language · Computer Science 2024-04-03 Ting-Rui Chiang , Xinyan Velocity Yu , Joshua Robinson , Ollie Liu , Isabelle Lee , Dani Yogatama

Recent progress in language modeling has been driven not only by advances in neural architectures, but also through hardware and optimization improvements. In this paper, we revisit the neural probabilistic language model (NPLM)…

Computation and Language · Computer Science 2021-04-09 Simeng Sun , Mohit Iyyer

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

Language models are at the core of natural language processing. The ability to represent natural language gives rise to its applications in numerous NLP tasks including text classification, summarization, and translation. Research in this…

Computation and Language · Computer Science 2019-11-19 Aisha Khatun , Anisur Rahman , Hemayet Ahmed Chowdhury , Md. Saiful Islam , Ayesha Tasnim

Highly regularized LSTMs achieve impressive results on several benchmark datasets in language modeling. We propose a new regularization method based on decoding the last token in the context using the predicted distribution of the next…

Computation and Language · Computer Science 2019-01-25 Siddhartha Brahma

Classifiers in natural language processing (NLP) often have a large number of output classes. For example, neural language models (LMs) and machine translation (MT) models both predict tokens from a vocabulary of thousands. The Softmax…

Machine Learning · Computer Science 2022-03-22 Andreas Grivas , Nikolay Bogoychev , Adam Lopez

We propose a new self-organizing hierarchical softmax formulation for neural-network-based language models over large vocabularies. Instead of using a predefined hierarchical structure, our approach is capable of learning word clusters with…

Computation and Language · Computer Science 2017-07-29 Yikang Shen , Shawn Tan , Chrisopher Pal , Aaron Courville

Neural Network Language Models (NNLMs) generate probability distributions by applying a softmax function to a distance metric formed by taking the dot product of a prediction vector with all word vectors in a high-dimensional embedding…

Machine Learning · Computer Science 2020-05-07 David Demeter , Gregory Kimmel , Doug Downey

Softmax is the de facto standard in modern neural networks for language processing when it comes to normalizing logits. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being…

Computation and Language · Computer Science 2022-05-20 Maxat Tezekbayev , Vassilina Nikoulina , Matthias Gallé , Zhenisbek Assylbekov

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the…

Computation and Language · Computer Science 2017-06-20 Edouard Grave , Armand Joulin , Moustapha Cissé , David Grangier , Hervé Jégou

Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering. In this…

Computation and Language · Computer Science 2017-08-09 Stephen Merity , Nitish Shirish Keskar , Richard Socher

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and…

Computation and Language · Computer Science 2019-07-01 Denis Emelin , Ivan Titov , Rico Sennrich

Existing language models (LMs) predict tokens with a softmax over a finite vocabulary, which can make it difficult to predict rare tokens or phrases. We introduce NPM, the first nonparametric masked language model that replaces this softmax…

Computation and Language · Computer Science 2023-05-29 Sewon Min , Weijia Shi , Mike Lewis , Xilun Chen , Wen-tau Yih , Hannaneh Hajishirzi , Luke Zettlemoyer

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

Computation and Language · Computer Science 2016-10-14 Yunchuan Chen , Lili Mou , Yan Xu , Ge Li , Zhi Jin

In spite of their superior performance, neural probabilistic language models (NPLMs) remain far less widely used than n-gram models due to their notoriously long training times, which are measured in weeks even for moderately-sized…

Computation and Language · Computer Science 2016-06-07 Andriy Mnih , Yee Whye Teh

Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the large parameter sizes and high computational complexity. By…

Computation and Language · Computer Science 2019-03-01 Liunian Harold Li , Patrick H. Chen , Cho-Jui Hsieh , Kai-Wei Chang

Large language models (LLMs) have made transformed changes for human society. One of the key computation in LLMs is the softmax unit. This operation is important in LLMs because it allows the model to generate a distribution over possible…

Machine Learning · Computer Science 2023-04-27 Yichuan Deng , Zhihang Li , Zhao Song