Improving multi-choice question answering by identifying essential terms in questions
Journal Title: Revista Romana de Interactiune Om-Calculator - Year 2018, Vol 11, Issue 2
Abstract
This paper describes a method for identifying the most relevant or essential terms in a question: the words that define the meaning of the question and whose removal makes it impossible to be answered correctly even by human agents. We use an artificial neural network architecture built upon semantic and syntactic features extracted from the question. The neural network prediction represents the degree to which the given term is essential to the question. The model has been trained and validated on a dataset consisting of 2233 questions and about human 18000 labeled terms with essentialness information. It achieves an F1 score of 0.80 which is similar to other state-of-the-art approaches but requires fewer features (15 compared to 120 features used by similar works) and is much easier to train. We further show how using only essential term information can improve the accuracy of a multi-choice question answering system, based on standard information retrieval (IR) techniques, by up to 4%.
Authors and Affiliations
George-Sebastian Pirtoaca, Stefan Ruseti, Traian Rebedea
Keywords
Related Articles
- EP ID EP673684
- DOI -
- Views 158
- Downloads 0
Interaction Techniques for Satellite Image Processing on the Grid
The current paper presents the Human-Computer interaction techniques, which follow from executing the business part of an application on the Grid. It presents the way in which such a software deals with data management,...
Online Support for Project Management Developed on Service-Oriented Architectures
Developing web interactive systems is a laborious work that requires the management of complex projects including data models, task models, and the user interface. In this paper are presented the main features of an onli...
A case study in specifying a formative index for the analysis of an e-learning application usability
Up to now few approaches to usability evaluation exist that are using structural models to analyze the causal relations between various factors influencing the quality of use and / or the intention to use. Also, few meas...
Experimentation of an acceptance model of e-learning systems
The aim of this paper is to test a model of acceptance of e-learning systems using the UTAUT reference model. After a brief description of UTAUT model, are described the proposed model and the assumptions, methods used a...
Utilizarea interfeţelor LabView pentru generarea formelor de undă şi a fişierelor specifice încercării aparatelor electrice de comutaţie
Lucrarea prezintă câteva aspecte ale activităţii desfaşurate in laborator pentru incercări de natură electrică efectuate aparatelor de comutaţie şi echipamentelor electrotehnice. Sunt evidenţiate elementele principale al...