A Study on Neural Network Language Modeling

نویسنده

  • Dengliang Shi
چکیده

An exhaustive study on neural network language modeling (NNLM) is performed in this paper. Different architectures of basic neural network language models are described and examined. A number of different improvements over basic neural network language models, including importance sampling, word classes, caching and bidirectional recurrent neural network (BiRNN), are studied separately, and the advantages and disadvantages of every technique are evaluated. Then, the limits of neural network language modeling are explored from the aspects of model architecture and knowledge representation. Part of the statistical information from a word sequence will loss when it is processed word by word in a certain order, and the mechanism of training neural network by updating weight matrixes and vectors imposes severe restrictions on any significant enhancement of NNLM. For knowledge representation, the knowledge represented by neural network language models is the approximate probabilistic distribution of word sequences from a certain training data set rather than the knowledge of a language itself or the information conveyed by word sequences in a natural language. Finally, some directions for improving neural network language modeling further is discussed.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Development of An Artificial Neural Network Model for Asphalt Pavement Deterioration Using LTPP Data

Deterioration models are important and essential part of any Pavement Management System (PMS). These models are used to predict future pavement situation based on existence condition, parameters causing deterioration and implications of various maintenance and rehabilitation policies on pavement. The majority of these models are based on roughness which is one of the most important indices in p...

متن کامل

A Neural-Network Approach to the Modeling of the Impact of Market Volatility on Investment

In recent years, authors have focused on modeling and forecasting volatility in financial series it is crucial for the characterization of markets, portfolio optimization and asset valuation. One of the most used methods to forecast market volatility is the linear regression. Nonetheless, the errors in prediction using this approach are often quite high. Hence, continued research is conducted t...

متن کامل

EFFECTS OF THE HARDENED NICKEL COATING ON THE FATIGUE BEHAVIOR OF CK45 STEEL: EXPERIMENTAL, FINITE ELEMENT METHOD, AND ARTIFICIAL NEURAL NETWORK MODELING

Hardened nickel coating is widely used in many industrial applications and manufacturing processes because of its benefits in improving the corrosion fatigue life. It is clear that increasing the coating thickness provides good protection against corrosion. However, it reduces the fatigue life. Thus, applying a thin layer of coated nickel might give an acceptable corrosion protection with minim...

متن کامل

Prediction of the Effect of Polymer Membrane Composition in a Dry Air Humidification Process via Neural Network Modeling

Utilization of membrane humidifiers is one of the methods commonly used to humidify reactant gases in polymer electrolyte membrane fuel cells (PEMFC). In this study, polymeric porous membranes with different compositions were prepared to be used in a membrane humidifier module and were employed in a humidification test. Three different neural network models were developed to investigate several...

متن کامل

Error Modeling in Distribution Network State Estimation Using RBF-Based Artificial Neural Network

State estimation is essential to access observable network models for online monitoring and analyzing of power systems. Due to the integration of distributed energy resources and new technologies, state estimation in distribution systems would be necessary. However, accurate input data are essential for an accurate estimation along with knowledge on the possible correlation between the real and...

متن کامل

Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm

Injection molding is one of the most important and common plastic formation methods. Combination of modeling tools and optimization algorithms can be used in order to determine optimum process conditions for the injection molding of a special part. Because of the complication of the injection molding process and multiplicity of parameters and their interactive effects on one another, analytical...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1708.07252  شماره 

صفحات  -

تاریخ انتشار 2017