16,814 Hits in 9.2 sec

A Survey of Information Retrieval Models for Malayalam Language Processing

Arjun Babu, Sindhu L.
2014 International Journal of Computer Applications  
Information retrieval is an important research area in computer science.  ...  In this survey paper we describe major IR models which are used for various document retrieval purposes.  ... [11] uses LSI technique with Singular Value Decomposition (SVD) to achieve effective indexing for English and Hindi languages.  ... 
doi:10.5120/18820-0230 fatcat:tm37gfyvrvbtfhyzzybow225bq


Jonathan Nau, Aluizio Haendchen Filho, Guilherme Passero
2017 PEOPLE International Journal of Social Sciences  
In this study, we combine latent semantic analysis (LSA) and a WordNet path-based similarity method using linear regression to predict scores for 76 short answers to three questions written by high school  ...  The presented approach may be used to support the automatic grading of short answer using supervised machine learning to weight different similarity scoring models.  ...  SVD (Singular Value Decomposition) of the matrix: The decomposition into singular values shows the correlations between words. 4.  ... 
doi:10.20319/pijss.2017.32.437450 fatcat:oychf4da75bfbptygk5kczhyfm

Latent Semantic Analysis [chapter]

P. Wiemer-Hastings
2006 Encyclopedia of Language & Linguistics  
Latent Semantic Analysis (LSA) is a technique for comparing texts using a vector-based representation that is learned from a corpus.  ...  The article also describes a few of the many successful applications of LSA to text-processing problems, and finishes by presenting a number of current research directions.  ...  LSA extends the vector-based approach by using Singular Value Decomposition (SVD) to reconfigure the data.  ... 
doi:10.1016/b0-08-044854-2/00870-1 fatcat:kxvhy42kl5br7dhhvomppc6oz4

Machine Learning Techniques with Ontology for Subjective Answer Evaluation

Syamala Devi M, Himani Mittal
2016 International Journal on Natural Language Computing  
Ten questions from Computer Graphics with sixty answers for each question are used for testing. The results are analyzed and it is concluded that the results are more accurate with use of Ontology.  ...  In this paper, the above mentioned techniques are implemented both with and without Ontology and tested on common input data consisting of technical answers of Computer Science.  ...  IMPLEMENTATION LSA technique is implemented in Java programming language and MatLab. MatLab is used for performing Singular Value Decomposition (SVD) for LSA.  ... 
doi:10.5121/ijnlc.2016.5201 fatcat:ub5aiy2dofavpbiiwtucqubzh4

Evaluation of Subjective Answers Using Glsa Enhanced With Contextual Synonymy

Parag A. Guruji, Mrunal M. Pagnis, Sayali M. Pawar, Prakash J. Kulkarni
2015 International Journal on Natural Language Computing  
This paper details experiments conducted under our project to build a software that evaluates the subjective answers of informative nature in a given knowledge domain.  ...  The model is tested by evaluating answers submitted by 61 students of Third Year B. Tech. CSE class of Walchand College of Engineering Sangli in a test on Database Engineering.  ...  Smriti Bhandari, for their valuable assistance in human expert grading of test answers used in training and testing of the system.  ... 
doi:10.5121/ijnlc.2015.4105 fatcat:74buuk4nvncahftqzdhclu6yqe

A Comparative Study of Modified Principal Component Analysis and Generalized Latent Semantic Analysis Approach to Automated Marking of Theoretical-Based Exams

Odunayo Esther Oduntan, Ibrahim Adepoju Adeyanju
2017 IOSR Journal of Mobile Computing & Application  
The reduced vector representation of the students' answers were graded according to the mark assigned to each question in the marking scheme using cosine similarity measure.  ...  MPCA and GLSA algorithms were used to reduce the sparseness of the DTM to obtain a vector representation of the students' answers and the marking scheme.  ...  In a computer based test, the examinee are made to make use of computer application consisting of questions to be answered, the examinee submits the page containing the answered questions electronically  ... 
doi:10.9790/0050-04023141 fatcat:wnrmk3rcxrf3hdvvizzwmm4jfa

Sparse Distributed Representations for Words with Thresholded Independent Component Analysis

Jaakko J. Vayrynen, Lasse Lindqvist, Timo Honkela
2007 Neural Networks (IJCNN), International Joint Conference on  
The applicability of the thresholded ICA representation is compared to singular value decomposition (SVD) in a multiple choice vocabulary task with three data sets.  ...  We show that independent component analysis (ICA) can be used to find distributed representations for words that can be further processed by thresholding to produce sparse representations.  ...  ACKNOWLEDGMENT This work was supported in part by the Helsinki Graduate School of Computer Science and Engineering, the Academy of Finland through the Finnish Centre of Excellence Programme and Nokia Foundation  ... 
doi:10.1109/ijcnn.2007.4371100 dblp:conf/ijcnn/VayrynenLH07 fatcat:dcquinsmk5cxvjws6qdvowvwfm

Adaptation of a Machine-learning Textual Entailment System to a Multilingual Answer Validation Exercise

Zornitsa Kozareva, Sonia Vázquez, Andrés Montoyo
2006 Conference and Labs of the Evaluation Forum  
In the case of Question Answering, textual entailment is represented as an answer validation exercise (AVE) where the system has to verify the correctness of the returned snippet of the Question Answering  ...  We have evaluated our approach with the English, Spanish, French, Dutch, German, Italian and Portuguese languages.  ...  In order to determine which values should be considered as more or less similar, we used a threshold.  ... 
dblp:conf/clef/KozarevaVM06a fatcat:j5xpjjgrardmtcyzqinndcpd2m

UPC-USMBA at SemEval-2017 Task 3: Combining multiple approaches for CQA for Arabic

Yassine El Adlouni, Imane Lahbari, Horacio Rodriguez, Mohammed Meknassi, Said Ouatik El Alaoui, Noureddine Ennahnahi
2017 Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)  
Our approach for facing the task is based on a performance of a set of atomic classifiers (lexical string-based, vectorial, and rulebased) whose results are later combined.  ...  This paper presents a description of the participation of the UPC-USMBA team in the SemEval 2017 Task 3, subtask D, Arabic.  ...  Question Answering, QA, i.e. querying a computer using Natural Language, is a traditional objective of Natural Language Processing.  ... 
doi:10.18653/v1/s17-2044 dblp:conf/semeval/AdlouniLRMAE17 fatcat:qz2xpf77rnf2xbue2lhtaigsxy

Automated Essay Rater using Natural Language Processing

Shristi Drolia, Shrey Rupani, Pooja Agarwal, Abheejeet Singh
2017 International Journal of Computer Applications  
This paper proposes a regression based approach for automatically scoring essays that are written in English.  ...  We also analyze how the essays are scored to get a better understanding about the proposed approach.  ...  Now in the term Document matrix we apply a mathematical technique called singular value Decomposition (SVD) to reduce the number of rows while preserving the similarity structure among the columns.  ... 
doi:10.5120/ijca2017913766 fatcat:aoafu75lurgp5jso7pfv6dfu3a

An Empirical Comparison of Text Categorization Methods [chapter]

Ana Cardoso-Cachopo, Arlindo L. Oliveira
2003 Lecture Notes in Computer Science  
We report the results obtained using the Mean Reciprocal Rank as a measure of overall performance, a commonly used evaluation measure for question answering tasks.  ...  In this paper we present a comprehensive comparison of the performance of a number of text categorization methods in two different data sets.  ...  It uses LSA/I to find similarities between the user's questions and questions that were previously answered by Unidata's personnel.  ... 
doi:10.1007/978-3-540-39984-1_14 fatcat:kcpemgdt4nczbbcfh7qdi2fwey

An autonomous assessment system based on combined latent semantic kernels

Young-Bum Kim, Yu-Seop Kim
2010 Expert systems with applications  
Many researchers have tried to integrate these two resources in many applications, to utilize diverse information extracted from each resource.  ...  We acquire a few combined kernel matrices which show various performances in experiments.  ...  Then we construct new semantic kernels from two matrices using the singular value decomposition (SVD) algorithm (Landauer et al., 1998) .  ... 
doi:10.1016/j.eswa.2009.09.058 fatcat:ekrf7rragnanphcqpwnlwqprbe

Concept based clustering for descriptive document classification

S. Senthamarai Kannan, N. Ramaraj
2007 Data Science Journal  
We present an approach for improving the relevance of search results by clustering the search results obtained for a query string with the help of a Concept Clustering Algorithm.  ...  This provides a more interactive and easier way to probe through search results and identifying the relevant documents for the users using the search engine.  ...  This uses a truncated singular value decomposition of the term-document matrix D.  ... 
doi:10.2481/dsj.6.91 fatcat:wqeqmgyb2vdl5dolp4xvhlsfg4

A Concept-Driven Algorithm for Clustering Search Results

S. Osinski, D. Weiss
2005 IEEE Intelligent Systems  
The Lingo algorithm According to the Collins English Dictionary, lingo is "a range of words or a style of language which is used in a particular situation or by a particular group of people."  ...  In fact, popular search engines, as opposed to query-answering systems, return Web pages matching the user's question rather than the question's answer.  ...  Similarly, column one represents D1 in figure 2a, "large-scale singular value computations," column two represents D2, "software for the sparse singular value decomposition," and so on.  ... 
doi:10.1109/mis.2005.38 fatcat:g2g5rzmuojawrmsf4dxb23td6e

A Heuristically Modified FP-Tree for Ontology Learning with Applications in Education [article]

Safwan Shatnawi, Mohamed Medhat Gaber, Mihaela Cocea
2019 arXiv   pre-print
Subject experts rated the quality of the system's answers on a subset of questions and their ratings were used to identify the most appropriate automatic semantic text similarity metric to use as a validation  ...  We employ the ontology in a question-answering system for students' content-related questions. For validation, we used textbook questions/answers and questions from online course forums.  ...  Funding: This study was self-funded as a part of a completed PhD by Safwan Shatnawi, supervised by Mohamed Medhat Gaber and Mihaela Cocea.  ... 
arXiv:1910.13561v1 fatcat:caznjgf35nc2tbyar6umd3bhny
« Previous Showing results 1 — 15 out of 16,814 results