English
Related papers

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

200 papers

Recent advances in language modeling consist in pretraining highly parameterized neural networks on extremely large web-mined text corpora. Training and inference with such models can be costly in practice, which incentivizes the use of…

Computation and Language · Computer Science 2024-04-12 Nathan Godey , Éric de la Clergerie , Benoît Sagot

The Softmax function on top of a final linear layer is the de facto method to output probability distributions in neural networks. In many applications such as language models or text generation, this model has to produce distributions over…

Machine Learning · Computer Science 2019-05-15 Octavian-Eugen Ganea , Sylvain Gelly , Gary Bécigneul , Aliaksei Severyn

Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can be a bottleneck of representational capacity of neural…

Machine Learning · Statistics 2018-05-29 Sekitoshi Kanai , Yasuhiro Fujiwara , Yuki Yamanaka , Shuichi Adachi

The Softmax bottleneck was first identified in language modeling as a theoretical limit on the expressivity of Softmax-based models. Being one of the most widely-used methods to output probability, Softmax-based models have found a wide…

Machine Learning · Computer Science 2021-10-12 Ying-Chen Lin

We introduce adaptive input representations for neural language modeling which extend the adaptive softmax of Grave et al. (2017) to input representations of variable capacity. There are several choices on how to factorize the input and…

Computation and Language · Computer Science 2019-02-26 Alexei Baevski , Michael Auli

Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies. Even then they struggle to predict rare or unseen words even if…

Computation and Language · Computer Science 2016-09-27 Stephen Merity , Caiming Xiong , James Bradbury , Richard Socher

Statistical language models are central to many applications that use semantics. Recurrent Neural Networks (RNN) are known to produce state of the art results for language modelling, outperforming their traditional n-gram counterparts in…

Computation and Language · Computer Science 2016-02-05 Anantharaman Palacode Narayana Iyer

In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and…

Computation and Language · Computer Science 2016-02-15 Rafal Jozefowicz , Oriol Vinyals , Mike Schuster , Noam Shazeer , Yonghui Wu

Language Modelling has been a central part of Natural Language Processing for a very long time and in the past few years LSTM-based language models have been the go-to method for commercial language modeling. Recently, it has been shown…

Computation and Language · Computer Science 2024-06-18 Jovan Andonov , Octavian Ganea , Paulina Grnarova , Gary Bécigneul , Thomas Hofmann

Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more…

Computation and Language · Computer Science 2018-06-20 Patrick H. Chen , Si Si , Yang Li , Ciprian Chelba , Cho-jui Hsieh

It is important to design compact language models for efficient deployment. We improve upon recent advances in both the language modeling domain and the model-compression domain to construct parameter and computation efficient language…

Computation and Language · Computer Science 2020-05-19 Zhongxia Yan , Hanrui Wang , Demi Guo , Song Han

This paper proposes a state-of-the-art recurrent neural network (RNN) language model that combines probability distributions computed not only from a final RNN layer but also from middle layers. Our proposed method raises the expressive…

Computation and Language · Computer Science 2018-09-03 Sho Takase , Jun Suzuki , Masaaki Nagata

Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive. We argue that the sub-optimal text generation is mainly attributable to the imbalanced token distribution, which particularly…

Computation and Language · Computer Science 2020-10-06 Byung-Ju Choi , Jimin Hong , David Keetae Park , Sang Wan Lee

Large Language Models (LLMs) struggle with complex reasoning due to limited diversity and inefficient search. We propose Soft Reasoning, an embedding-based search framework that optimises the embedding of the first token to guide…

Computation and Language · Computer Science 2025-09-16 Qinglin Zhu , Runcong Zhao , Hanqi Yan , Yulan He , Yudong Chen , Lin Gui

To encourage intra-class compactness and inter-class separability among trainable feature vectors, large-margin softmax methods are developed and widely applied in the face recognition community. The introduction of the large-margin concept…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-22 Jingjing Huo , Yingbo Gao , Weiyue Wang , Ralf Schlüter , Hermann Ney

Out-of-vocabulary words account for a large proportion of errors in machine translation systems, especially when the system is used on a different domain than the one where it was trained. In order to alleviate the problem, we propose to…

Computation and Language · Computer Science 2016-08-08 Pranava Swaroop Madhyastha , Cristina España-Bonet

Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern transformer-based LM, are the pointer networks redundant…

Computation and Language · Computer Science 2023-05-23 Haw-Shiuan Chang , Zonghai Yao , Alolika Gon , Hong Yu , Andrew McCallum

The Softmax function is used in the final layer of nearly all existing sequence-to-sequence models for language generation. However, it is usually the slowest layer to compute which limits the vocabulary size to a subset of most frequent…

Computation and Language · Computer Science 2019-03-25 Sachin Kumar , Yulia Tsvetkov

Unsupervised neural grammar induction aims to learn interpretable hierarchical structures from language data. However, existing models face an expressiveness bottleneck, often resulting in unnecessarily large yet underperforming grammars.…

Computation and Language · Computer Science 2025-09-26 Jinwook Park , Kangil Kim

Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the…

Computation and Language · Computer Science 2019-06-25 Mingda Chen , Kevin Gimpel
‹ Prev 1 2 3 10 Next ›