A complete automatic short answer assessment system with student identification

Suwanwiwat, Hemmaphan; Blumenstein, Michael; Pal, Umapada

doi:10.1109/icdar.2015.7333834

Cited by 6 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Newly proposed combined feature extraction techniques called WRL_MDGGF and G_WRL_MDGGF, together with the original MDF, the original GGF, and their combined techniques, namely G_MDF [3], G_GGF [3] were employed in the proposed SAAS. These techniques had different feature vector sizes.…”

Section: Feature Extraction Techniquesmentioning

confidence: 99%

“…c) Centre of Gravity Feature (referred to as G): The centre of gravity feature was extracted from nine images comprised of a full boundary image, two equal horizontal and two equal vertical windows, and four equal windows which were obtained from dividing each full image into four equal windows. The centre of gravity vector size is 18 [3].…”

Section: Feature Extraction Techniquesmentioning

confidence: 99%

“…These features were selected to create a combined feature extraction technique due to their ability to successfully extract important features from images. Furthermore, their properties can be found in some or all English alphabets, which have enabled accurate recognition rates to be attained in a number of applications [1], [2], and [3].…”

Section: ) the Proposed Water Reservoir Loop Modified Direction Andmentioning

confidence: 99%

“…The newly proposed G_WRL_MDGGF was created in an attempt to increase the recognition and accuracy rates. The reason for adding centre of gravity feature into the WRL_MDGGF vector was because positive outcomes were obtained when enhancing the original MDF, and GGF with centre of gravity feature [3]. The G_WRL_MDGGF feature vector is 1,587 which was obtained from 392 of WRF + 192 of LF + 121 of the MDF + 864 of the GGF 18 of the centre of gravity feature.…”

Section: B) the Proposed Gravity Water Reservoir Loop Modified Dirmentioning

confidence: 99%

“…a) The Gravity, Modified Direction Feature (G_MDF): The recently proposed G_MDF [3] is a combined technique combining centre of gravity feature into its feature vector. The G_MDF vector size was 139; this obtained from 121 of the MDF + 18 from G vector).…”

Section: B) the Proposed Gravity Water Reservoir Loop Modified Dirmentioning

confidence: 99%

See 4 more Smart Citations

An Investigation of Novel Combined Features for a Handwritten Short Answer Assessment System

Suwanwiwat

Pal

Blumenstein

2016

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)

Self Cite

View full text Add to dashboard Cite

This paper proposes an off-line automatic assessment system utilising novel combined feature extraction techniques. The proposed feature extraction techniques are 1) the proposed Water Reservoir, Loop, Modified Direction and Gaussian Grid Feature (WRL_MDGGF), 2) the proposed Gravity, Water Reservoir, Loop, Modified Direction and Gaussian Grid Feature (G_WRL_MDGGF). The proposed feature extraction techniques together with their original features and other combined feature extraction techniques were employed in an investigation of the efficiency of feature extraction techniques on an automatic off-line short answer assessment system. The proposed system utilised two classifiers namely, artificial neural networks and Support Vector Machines (SVMs), two type of datasets and two different thresholds in this investigation. Promising recognition rates of 94.85% and 94.88% were obtained when the proposed WRL_MDGGF and G_WRL_MDGGF were employed, respectively, using SVMs.

show abstract

Section: Feature Extraction Techniquesmentioning

confidence: 99%

Section: Feature Extraction Techniquesmentioning

confidence: 99%

Section: ) the Proposed Water Reservoir Loop Modified Direction Andmentioning

confidence: 99%

Section: B) the Proposed Gravity Water Reservoir Loop Modified Dirmentioning

confidence: 99%

Section: B) the Proposed Gravity Water Reservoir Loop Modified Dirmentioning

confidence: 99%

See 3 more Smart Citations

An Investigation of Novel Combined Features for a Handwritten Short Answer Assessment System

Suwanwiwat

Pal

Blumenstein

2016

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)

Self Cite

View full text Add to dashboard Cite

show abstract

A novel multi-task learning technique for offline handwritten short answer spotting and recognition

Das,

Suwanwiwat,

Pal

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Question Answering Over Knowledge Base: A Scheme for Integrating Subject and the Identified Relation to Answer Simple Questions

Buzaaba

Amagasa

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Answering natural language question over a knowledge base is an important and challenging task with a wide range of application in natural language processing and information retrieval. Several existing knowledge-based question answering systems exploit complex end-to-end neural network approaches that are computationally expensive and take long to execute when training the neural network. More importantly, such an end-to-end approach makes it difficult to examine the process of query processing. In this study, we decompose the question answering problem in a three-step pipeline of entity detection, entity linking, and relation prediction, and solve each component separately. We explore basic neural network and non-neural network methods for entity detection and relation prediction plus a few heuristics for entity linking. We also introduce a method to identify ambiguity in the data and show that ambiguity in the data bounds the performance of the question answering system. The experiment on the SimpleQuestions benchmark data set shows that a combination of basic LSTMs, GRUs, and non-neural network techniques achieve reasonable performance while providing an opportunity to understand the question answering problem structure.

show abstract

A complete automatic short answer assessment system with student identification

Cited by 6 publications

References 7 publications

An Investigation of Novel Combined Features for a Handwritten Short Answer Assessment System

An Investigation of Novel Combined Features for a Handwritten Short Answer Assessment System

A novel multi-task learning technique for offline handwritten short answer spotting and recognition

Question Answering Over Knowledge Base: A Scheme for Integrating Subject and the Identified Relation to Answer Simple Questions

Contact Info

Product

Resources

About