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
Quantifying and Visualizing the Demand and Supply Gap from E-commerce Search Data using Topic Models
Anjan Goswami,Prasant Mohapatra,ChengXiang Zhai +2 more
- 13 May 2019
TL;DR: This paper shows how digitized product data and the historical search logs can be used in understanding and quantifying the gap between the supply and demand side of a retail market, and defines a metric based on Kullback-Leibler (KL) divergence of topic distributions of queries and the products.
8
The End of the Policy Analyst? Testing the Capability of Artificial Intelligence to Generate Plausible, Persuasive, and Useful Policy Analysis
Mehrdad Safaei,Justin Longo +1 more
- 18 Aug 2023
TL;DR: The current NLP tools are not capable of generating fully useful policy briefing notes, but they can serve as a supplement to human analysts and have the potential to improve the quality of future policy analysis.
8
•Posted Content
Deconstructing and reconstructing word embedding algorithms
TL;DR: This work deconstructs Word2vec, GloVe, and others, into a common form, unveiling some of the necessary and sufficient conditions required for making performant word embeddings, and demonstrates that these two algorithmic features are sufficient conditions to construct a novel word embedding algorithm, Hilbert-MLE.
8
Imputation of missing time-activity data with long-term gaps: A multi-scale residual CNN-LSTM network model
Youngseob Eum,Eun-Hye Yoo +1 more
TL;DR: Wang et al. as mentioned in this paper proposed a two-step imputation method to address the missing data with long-term gaps, based on both efficient representation of TA patterns and high regularity in TA data.
8
Emotion Detection with Neural Personal Discrimination
Xiabing Zhou,Zhongqing Wang,Shoushan Li,Guodong Zhou,Min Zhang +4 more
- 01 Nov 2019
TL;DR: Zhang et al. as mentioned in this paper proposed a Neural Personal Discrimination (NPD) approach to address the problem of capturing attributes-aware words to connect similar people in social media by determining personal attributes from posts and connecting relevant posts with similar attributes to learn their emotions.
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
[...]