scholarly journals Three-stage question answering system with sentence ranking

10.29007/bj7w ◽  
2019 ◽  
Author(s):  
Daria Soboleva ◽  
Konstantin Vorontsov
Keyword(s):  
Neural Network ◽  
High Speed ◽  
Question Answering ◽  
Feature Space ◽  
Second Step ◽  
Question Answering System ◽  
The Third ◽  
Construction Techniques ◽  
Space Construction ◽  
Speed Up

We explore a recently proposed question answering system. We developed a high speed modification based on dividing the question answering system into three consecutive stages. The first step is to find the candidate documents that most likely contain the answer to the question. The second step is to rank sentences by the probability of having a correct answer to the question. The third step is to find the exact phrase that answers the question. At the third step we used a recently proposed recurrent bidirectional neural network predicting the beginning and the end of a response. In this paper we showed that the proposed question answering system allows to speed up its work without significant losses in the quality. For each step we also explored the feature space construction techniques allowing to improve the final quality.

Bayesian Probability and Tanimoto Based Recurrent Neural Network for Question Answering System

2021 ◽  
Author(s):  
Veeraraghavan Jagannathan
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Question Answering ◽  
Bayesian Probability ◽  
Significant Information ◽  
Continuous Increase ◽  
Question Answering System ◽  
Relevant Result ◽  
Proper Nouns ◽  
Different Types

Question Answering (QA) has become one of the most significant information retrieval applications. Despite that, most of the question answering system focused to increase the user experience in finding the relevant result. Due to the continuous increase of web content, retrieving the relevant result faces a challenging issue in the Question Answering System (QAS). Thus, an effective Question Classification (QC), and retrieval approach named Bayesian probability and Tanimoto-based Recurrent Neural Network (RNN) are proposed in this research to differentiate the types of questions more efficiently. This research presented an analysis of different types of questions with respect to the grammatical structures. Various patterns are identified from the questions and the RNN classifier is used to classify the questions. The results obtained by the proposed Bayesian probability and Tanimoto-based RNN showed that the syntactic categories related to the domain-specific types of proper nouns, numeral numbers, and the common nouns enable the RNN classifier to reveal better result for different types of questions. However, the proposed approach obtained better performance in terms of precision, recall, and F-measure with the values of 90.14, 86.301, and 90.936 using dataset-2.

scholarly journals A Hybrid Neural Network BERT-Cap Based on Pre-Trained Language Model and Capsule Network for User Intent Classification

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Hai Liu ◽  
Yuanxia Liu ◽  
Leung-Pun Wong ◽  
Lap-Kei Lee ◽  
Tianyong Hao
Keyword(s):  
Neural Network ◽  
Neural Network Model ◽  
Question Answering ◽  
Semantic Information ◽  
Language Model ◽  
Dialogue System ◽  
Hybrid Neural Network ◽  
Question Answering System ◽  
User Intent ◽  
Vital Component

User intent classification is a vital component of a question-answering system or a task-based dialogue system. In order to understand the goals of users’ questions or discourses, the system categorizes user text into a set of pre-defined user intent categories. User questions or discourses are usually short in length and lack sufficient context; thus, it is difficult to extract deep semantic information from these types of text and the accuracy of user intent classification may be affected. To better identify user intents, this paper proposes a BERT-Cap hybrid neural network model with focal loss for user intent classification to capture user intents in dialogue. The model uses multiple transformer encoder blocks to encode user utterances and initializes encoder parameters with a pre-trained BERT. Then, it extracts essential features using a capsule network with dynamic routing after utterances encoding. Experiment results on four publicly available datasets show that our model BERT-Cap achieves a F1 score of 0.967 and an accuracy of 0.967, outperforming a number of baseline methods, indicating its effectiveness in user intent classification.

scholarly journals A New Concept of the Mechanism of Variation of Tribological Properties of the Machine Elements Interacting Surfaces

2020 ◽  
Author(s):  
George Tumanishvili ◽  
Tengiz Nadiradze ◽  
Giorgi Tumanishvili
Keyword(s):  
Contact Zone ◽  
Tribological Properties ◽  
High Speed ◽  
Third Body ◽  
The Third ◽  
The Coefficient Of Friction ◽  
Speed Up ◽  
Machine Elements ◽  
Interacting Surfaces ◽  
Experimental Researches

The methods of estimation and prediction of tribological properties of the contact zone of interacting elements of machines are characterized by the low informativeness and accuracy that complicates provision of the proper tribological properties and hinders reliable and effective operation of machines. For obtaining more wide information about factors influencing tribological properties of the interacting surfaces, the experimental researches on the high speed (up to 70-m/s) and serial twin-disk machines were carried out. Our researches have shown that with different properties and degrees of destruction of the third body, the coefficient of friction can change up to 10 times or more, the wear rate up to 102-104 times, etc. This was the basis for a new concept of the mechanism of variation of tribological properties of interacting surfaces. The researches have shown a dependence of tribological properties of the contact zone on the properties and destruction degree of the third body that was assumed as a basis of new concept of the mechanism of variation of tribological properties of these surfaces. The monitoring of the third body destruction onset and development was carried out in the laboratory conditions and a criterion of the third body destruction was developed. The reasons of the negative, neutral and positive friction and mild, severe and catastrophic wear are shown.

scholarly journals Chatbot Analytics Based on Question Answering System Movie Related Chatbot Case Analytics.pdf

2020 ◽  
Author(s):  
Jugal Shah ◽  
Sabah Mohammed
Keyword(s):  
Neural Network ◽  
Question Answering ◽  
Question Answering System

In this paper, an attempt has been made to understand<br>the importance of a neural network-based chatbot system for<br>movie-related queries.<br>

Bogdanov–Takens Bifurcation in a Neutral Delayed Hopfield Neural Network with Bidirectional Connection

2020 ◽  
Vol 13 (06) ◽  
pp. 2050049
Author(s):  
Houssem Achouri ◽  
Chaouki Aouiti ◽  
Bassem Ben Hamed
Keyword(s):  
Neural Network ◽  
Normal Form ◽  
Characteristic Equation ◽  
Center Manifold ◽  
Hopfield Neural Network ◽  
Second Step ◽  
Double Zero ◽  
The Third ◽  
Dynamical Behaviors ◽  
Linearized System

In this paper, a neutral Hopfield neural network with bidirectional connection is considered. In the first step, by choosing the connection weights as parameters bifurcation, the critical point at which a zero root of multiplicity two occurs in the characteristic equation associated with the linearized system. In the second step, we studied the zeros of a third degree exponential polynomial in order to make sure that except the double zero root, all the other roots of the characteristic equation have real parts that are negative. Moreover, we find the critical values to guarantee the existence of the Bogdanov–Takens bifurcation. In the third step, the normal form is obtained and its dynamical behaviors are studied after the use of the reduction on the center manifold and the theory of the normal form. Furthermore, for the demonstration of our results, we have given a numerical example.

Sign in / Sign up

Export Citation Format

Share Document