A primer on neural network models for natural language processing
TL;DR: This tutorial surveys neural network models from the perspective of natural language processing research, in an attempt to bring natural-language researchers up to speed with the neural techniques.
read more
Abstract: Over the past few years, neural networks have re-emerged as powerful machine-learning models, yielding state-of-the-art results in fields such as image recognition and speech processing. More recently, neural network models started to be applied also to textual natural language signals, again with very promising results. This tutorial surveys neural network models from the perspective of natural language processing research, in an attempt to bring natural-language researchers up to speed with the neural techniques. The tutorial covers input encoding for natural language tasks, feed-forward networks, convolutional networks, recurrent networks and recursive networks, as well as the computation graph abstraction for automatic gradient computation.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Supervisión remota en el entrenamiento de un clasificador de sentimientos en comentarios turísticos
C. A. Martín,Rosa María Aguilar,Jesús M. Torres,Sonia Pértega Díaz +3 more
- 06 Mar 2020
TL;DR: In this article, an algorithm for automatically identifying the sentiments expressed by tourists on eWOM (Electronic Word of Mouth) platforms is described. But the authors do not present a use case for this method involving a group of hotels located on the island of Tenerife (Canary Islands).
•Dissertation
Aprendizagem profunda para reconhecimento de entidades nomeadas em domínio jurídico
Pedro Vitor Quinta de Castro
- 05 Dec 2019
TL;DR: Reconhecimento de Entidades Nomeadas (REN) and uma tarefa desafiadora em Processamento de Linguagem Natural, for uma lingua tao rica quanto o Portuguesa, have been evaluated in this article.
An Efficient Intrusion Detection Model Combined Bidirectional Gated Recurrent Units With Attention Mechanism
Jingyi Wang,Chen Naiyue,Jinhui Yu,Jin Yi,Li Yidong +4 more
- 05 Nov 2020
TL;DR: Wang et al. as mentioned in this paper proposed a two-layer bidirectional gated recurrent unit (BiGRU) network with attention mechanism to classify traffic data, which can detect network intrusions effectively and outperform other related methods with reduction of false alarm rate, high accuracy rate, reduced training and testing time.
5
KazNewsDataset: Single Country Overall Digital Mass Media Publication Corpus
Kirill Yakunin,Maksat Kalimoldayev,Ravil I. Mukhamediev,Rustam Mussabayev,V. B. Barakhnin,Yan Kuchin,Sanzhar Murzakhmetov,Timur Buldybayev,Ulzhan Ospanova,Marina Yelis,Akylbek Zhumabayev,Viktors I. Gopejenko,Zhazirakhanym Meirambekkyzy,Alibek Abdurazakov +13 more
- 14 Mar 2021
TL;DR: In this article, the authors present a corpus of Kazakhstan media, which contains over 4 million publications from 36 primary sources (which has at least 500 publications), including more than 2 million texts of Russian media for comparative analysis of publication activity of the countries, also about 4000 sections of state policy documents.
5
•Posted Content
Deep Dialog Act Recognition using Multiple Token, Segment, and Context Information Representations
TL;DR: The authors explored means to generate more informative segment representations, not only by exploring different network architectures, but also by considering different token representations at both the word level and the character and functional level.
5
References
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
•Posted Content
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
82.5K
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
- 01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
53.5K
Related Papers (5)
Jeffrey Pennington,Richard Socher,Christopher D. Manning +2 more
- 01 Oct 2014
[...]