Filters








430,236 Hits in 5.8 sec

A Question Answering System Based on Vector Similarity

Takuya Kosugi, Hiroya Susuki, Hiroyuki Okamoto, Hiroaki Saito
2004 NTCIR Conference on Evaluation of Information Access Technologies  
This paper reports on an implementation of a question answering system with the vector similarity scoring method. Our question answering system consists of four modules.  ...  The evaluation of our system on NTCIR Question Answering Challenge 2 is 0.242 in recall, 0.095 in precision, 0.137 in F-measure and 0.231 in MRR.  ...  Conclusion We have implemented and evaluated a question answering system which selects answers based on the vector similarity. This system has attained MRR=0.231 in QAC2.  ... 
dblp:conf/ntcir/KosugiSOS04 fatcat:xlu2yphvgrfllf5xzdr4wv4xpe

VectorSLU: A Continuous Word Vector Approach to Answer Selection in Community Question Answering Systems

Yonatan Belinkov, Mitra Mohtarami, Scott Cyphers, James Glass
2015 Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  
Continuous word and phrase vectors have proven useful in a number of NLP tasks.  ...  , good, and bad with regards to their corresponding questions; and YES/NO inference for predicting a yes, no, or unsure response to a YES/NO question using all of its good answers.  ...  We would like to thank Alessandro Moschitti, Preslav Nakov, Lluís Màrquez, Massimo Nicosia, and other members of the QCRI Arabic Language Technologies group for their collaboration on this project.  ... 
doi:10.18653/v1/s15-2048 dblp:conf/semeval/BelinkovMCG15 fatcat:qymsjdycyzbsrlwmc3vamgru6i

Using Vector Space Model in Question Answering System

Jovita, Linda, Andrei Hartawan, Derwin Suhartono
2015 Procedia Computer Science  
The objective of this research is to represent knowledge and retrieve the answer for a given question by utilizing Vector Space Model.  ...  The query will be compared to the knowledge based by measuring their similarity.  ...  Relevance from a document to query is based on the similarity between document vector and query vector 8 .  ... 
doi:10.1016/j.procs.2015.07.570 fatcat:l66ws42uibhhran2vtyfbdhb44

Question Answering System Using Concept-Based Vector Space Model

Isrami Ismail, Takashi Yukawa
2004 NTCIR Conference on Evaluation of Information Access Technologies  
One major concept of this system is the idea of placing the whole data set in the concept -based vector space, and searching of the answer for each question is done by calculating the nearest newspaper's  ...  This paper presents the architecture of the Concept-based Vector Space Mod el Question Answering System ( CBVSM-QAS) develop ed at the Nagaoka University of Technology (NUT) and used in the 4-th NTCIR  ...  Section A of this system, which refers to the generation of concept-based and document base vector remains the same as the previous one.  ... 
dblp:conf/ntcir/IsmailY04 fatcat:njviii3se5f4hiqoxcvuzxls3a

Design and Implementation of English Intelligent Communication Platform Based on Similarity Algorithm

Yujie Chai, Wei Wang
2021 Complexity  
In response to the shortcomings of existing sentence vector representation models and the singularity of text similarity algorithms, improved models and algorithms are proposed based on a thorough study  ...  The algorithm first improves the deficiencies of the traditional word-shift distance algorithm by defining multifeature fusion weights and realizes a text similarity calculation algorithm based on multifeature  ...  Related Work e knowledge ontology base is a "question-answer" base of user questions, and the answers to these questions are stored in a database.  ... 
doi:10.1155/2021/5575417 fatcat:v7cf63uuarbbxbtpk6h2kjd7hm

JAIST: Combining multiple features for Answer Selection in Community Question Answering

Quan Hung Tran, Vu Tran, Tu Vu, Minh Nguyen, Son Bao Pham
2015 Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  
In this paper, we describe our system for SemEval-2015 Task 3: Answer Selection in Community Question Answering.  ...  In this task, the systems are required to identify the good or potentially good answers from the answer thread in Community Question Answering collections.  ...  System Description For extracting the features, we first preprocess the questions and the answers then build a number of models based on training data or other sources (Figure 1 ).  ... 
doi:10.18653/v1/s15-2038 dblp:conf/semeval/TranTVNP15 fatcat:3qi3fw4ktrd4tab5bsgpwxtpbm

Application of Knowledge Map Based on BiLSTM-CRF Algorithm Model in Ideological and Political Education Question Answering System

Wei Zhao, Juan Liu, Chia-Huei Wu
2022 Mobile Information Systems  
In order to solve this problem, this paper designs a question answering system for ideological and political education based on BiLSTM-CRF algorithm model (BiLSTM: Bidirectional Long Short-Term Memory  ...  Traditional automatic question answering methods usually rely on predicates and other prior information to achieve knowledge base question answering, which requires a lot of manpower and poor generalization  ...  A knowledge base question answer task is to answer a natural language question using one or more knowledge triples in the knowledge base.  ... 
doi:10.1155/2022/4139323 fatcat:yuagi7kpy5b45i4rrapyyme54i

Answer Selection in Arabic Community Question Answering: A Feature-Rich Approach

Yonatan Belinkov, Alberto Barrón-Cedeño, Hamdy Mubarak
2015 Proceedings of the Second Workshop on Arabic Natural Language Processing  
The recent SemEval-2015 introduced a shared task on community question answering, providing a corpus and evaluation scheme. In this paper we address the problem of answer selection in Arabic.  ...  The task of answer selection in community question answering consists of identifying pertinent answers from a pool of user-generated comments related to a question.  ...  It is part of the Interactive sYstems for Answer Search (Iyas) project.  ... 
doi:10.18653/v1/w15-3223 dblp:conf/wanlp/BelinkovBM15 fatcat:y45iq7vy3vdzbkrrwymd373vq4

SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings [article]

Todor Mihaylov, Preslav Nakov
2019 arXiv   pre-print
We describe our system for finding good answers in a community forum, as defined in SemEval-2016, Task 3 on Community Question Answering.  ...  Our approach relies on several semantic similarity features based on fine-tuned word embeddings and topics similarities.  ...  It is also part of the Interactive sYstems for Answer Search (Iyas) project, which is developed by the Arabic Language Technologies (ALT) group at the Qatar Computing Research Institute, HBKU, part of  ... 
arXiv:1911.08743v1 fatcat:55yw5kuspbbodotqhmdz3lyj24

Sentence Extraction for Machine Comprehension

2019 International journal of recent technology and engineering  
Question answering system is one such variant used to find the correct 'answer' for a 'query' using the supplied 'context'.  ...  This work devises a method for sentence selection that uses cosine similarity and common word count between each sentence of context and question.  ...  Research in this area ranges from simple answer extraction to neural networks based systems for spotting answers in the given content.  ... 
doi:10.35940/ijrte.b3095.078219 fatcat:7y2cdefbrva5jmztfyhhluknim

Al-Bayan: A Knowledge-based System for Arabic Answer Selection

Reham Mohamed, Maha Ragab, Heba Abdelnasser, Nagwa M. El-Makky, Marwan Torki
2015 Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  
We propose a knowledge-based solution for answer selection of Arabic questions, specialized for Islamic sciences.  ...  We build a Semantic Interpreter to evaluate the semantic similarity between Arabic question and answers using our Quranic ontology of concepts.  ...  We use these vectors to compute a semantic similarity score between the question and each candidate answer.  ... 
doi:10.18653/v1/s15-2040 dblp:conf/semeval/MohamedRAET15 fatcat:dwfol3jpg5ednabvxmf6heovyu

IMPLEMENTATION OF GENERALIZED VECTOR SPACE MODEL METHOD AT AUTOMATIC ASSESSMENT OF ONLINE ESSAY EXAM

Muhammad Arafah
2018 Journal of Information Technology and Its Utilization  
The results of this study indicate that the automatic scoring system with the GVSM weighting method and the cosine similarity similarity calculation method have the accuracy of the assessment with an average  ...  The aim of the study was to design and implement automatic testing of online essay examinations using the Generalized Vector Space Model (GVSM) method.  ...  Sort documents based on similarity, by calculating vector multiplication: When: 𝑑 𝑗 ⃗⃗⃗⃗ : Vector document j 𝑞 : Vector query F. Software Used 1.  ... 
doi:10.30818/jitu.1.2.1893 fatcat:w35ugtulqvaxtbkh6fmyxl3xdy

Knowledge Base Question Answering Based on Deep Learning Models [chapter]

Zhiwen Xie, Zhao Zeng, Guangyou Zhou, Tingting He
2016 Lecture Notes in Computer Science  
This paper focuses on the task of knowledge-based question answering (KBQA). KBQA aims to match the questions with the structured semantics in knowledge base.  ...  The evaluation result shows that our system achieves an AverageF1 measure of 79.57% on test dataset.  ...  Most of the KBQA systems are based on semantic parsing, where a question is converted into logical form and then transformed into structured query to be executed on knowledge base.  ... 
doi:10.1007/978-3-319-50496-4_25 fatcat:bwnxuqmqxfedti6uyjuostt7r4

A Model of Convolutional Neural Network Combined with External Knowledge to Measure the Question Similarity for Community Question Answering Systems

Van-Tu Nguyen, VNU University of Engineering and Technology, Ha Noi City, Vietnam, Anh-Cuong Le, Ha-Nam Nguyen
2021 International Journal of Machine Learning and Computing  
Automatically determining similar questions and ranking the obtained questions according to their similarities to each input question is a very important task to any community Question Answering system  ...  To this objective, we propose a neural network-based model which combines a Convolutional Neural Network (CNN) with features from other methods so that the deep learning model is enhanced with addtional  ...  As the result, based on word embedding, we have obtained new features representing the similarity between the input question and a related question and its answers.  ... 
doi:10.18178/ijmlc.2021.11.3.1035 fatcat:5ntmfmg625anzgbplipa5n2jxi

Attention-based Pairwise Multi-Perspective Convolutional Neural Network for Answer Selection in Question Answering [article]

Jamshid Mozafari, Mohammad Ali Nematbakhsh, Afsaneh Fatemi
2019 arXiv   pre-print
A component of these systems is Answer Selection which selects the most relevant from candidate answers.  ...  Over the past few years, question answering and information retrieval systems have become widely used. These systems attempt to find the answer of the asked questions from raw text sources.  ...  There are two kinds of question answering systems containing Knowledge-based and Information Retrieval-based (IR-based) systems.  ... 
arXiv:1909.01059v3 fatcat:gv2i7hgzpnfldd6zqb3sztppt4
« Previous Showing results 1 — 15 out of 430,236 results