• Journal of Digital Contents Society
• /
• v.19 no.5
• /
• pp.927-933
• /
• 2018

One of the factors that have the greatest influence on the error of the question answering system that finds and provides answers to natural language questions is the step of searching for documents or passages that contain correct answers. In order to improve the retrieval performance, it is necessary to understand the characteristics of documents and passages containing correct answers. This paper experimentally analyzes how many question words appear in the correct answer documents, how the location of the question word is distributed, and how the topic of the question and the correct answer document are similar using the corpus composed of the question, the documents with correct answer, and the documents without correct answer. This study explains the causes of previous search research results for question answer system and discusses the necessary elements of effective search step.

• The Journal of the Korea Contents Association
• /
• v.5 no.3
• /
• pp.209-215
• /
• 2005

In this paper, we describe the answer pattern for definitional question-answering system. The .answer extraction method of a definitional question-answering system is different from the general answer extraction method because it presents the descriptive answer for a definitional question. The definitional answer extraction using the definitional answer pattern can extract the definitional answer correctly without the semantic analysis. The definitional answer pattern is consist of answer pattern, conditional rule and priority to extract the correct definitional answer. We extract the answer pattern from the definitional training corpus and determine the optimum conditional rule using F-measure. Next, we determine the priority of answer patterns using precision and syntactic structure. Our experiments show that our approach results in the precision(0.8207), the recall(0.9268) and the F-measure(0.8705). It means that our approach can be used efficiently for a definitional question-answering system.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• The Journal of the Korea Contents Association
• /
• v.11 no.3
• /
• pp.73-83
• /
• 2011

The question answering system shows the answers that are input by other users for user's question. In spite of many researches to try to enhance the satisfaction level of answers for user question, there is a essential limitation. So, the question answering system provides users with the method of recommendation of another questions that can satisfy user's intention with high probability as an auxiliary function. The method using the fuzzy relational product operator was proposed for recommending the questions that can includes largely the contents of the user's question. The fuzzy relational product operator is composed of the Kleene-Dienes operator to measure the implication degree by contents between two questions. However, Kleene-Dienes operator is not fit to be the right operator for finding a question answers pair that semantically includes a user question, because it was not designed for the purpose of finding the degree of semantic inclusion between two documents. We present a novel fuzzy implication operator that is designed for the purpose of finding question answer pairs by considering implication relation. The new operator calculates a degree that the question semantically implies the other question. We show the experimental results that the probability that users are satisfied with the searched results is increased when the proposed operator is used for recommending of question answering system.

• ETRI Journal
• /
• v.31 no.4
• /
• pp.419-428
• /
• 2009

A question answering (QA) system can be built using multiple QA modules that can individually serve as a QA system in and of themselves. This paper proposes a learnable, strategy-driven QA model that aims at enhancing both efficiency and effectiveness. A strategy is learned using a learning-based classification algorithm that determines the sequence of QA modules to be invoked and decides when to stop invoking additional modules. The learned strategy invokes the most suitable QA module for a given question and attempts to verify the answer by consulting other modules until the level of confidence reaches a threshold. In our experiments, our strategy learning approach obtained improvement over a simple routing approach by 10.5% in effectiveness and 27.2% in efficiency.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.448-451
• /
• 2005

In this paper, we describe a method of answer extraction on a concept-based question-answering system. The concept-based question answering system is a system which extract answer using concept information. we have researched the method of answer extraction using concepts which analyzed and extracted through question analysing with answer extracting rules. We analyzed documents including answers and then composed answer extracting rules. Rules consist of concept and syntactic information, we generated candidates of answer through the rules and then chose answer.

• ETRI Journal
• /
• v.42 no.2
• /
• pp.239-246
• /
• 2020

Recently, Linked Open Data has become a large set of knowledge bases. Therefore, the need to query Linked Data using question answering (QA) techniques has attracted the attention of many researchers. A QA system translates natural language questions into structured queries, such as SPARQL queries, to be executed over Linked Data. The two main challenges in such systems are lexical and semantic gaps. A lexical gap refers to the difference between the vocabularies used in an input question and those used in the knowledge base. A semantic gap refers to the difference between expressed information needs and the representation of the knowledge base. In this paper, we present a novel method using an ontology lexicon and dependency parse trees to overcome lexical and semantic gaps. The proposed technique is evaluated on the QALD-5 benchmark and exhibits promising results.

• Asia pacific journal of information systems
• /
• v.25 no.4
• /
• pp.686-711
• /
• 2015

The performance of a novel medical question-answering engine called CliniCluster and existing search engines, such as CQA-1.0, Google, and Google Scholar, was evaluated using known-item searching. Known-item searching is a document that has been critically appraised to be highly relevant to a therapy question. Results show that, using CliniCluster, known-items were retrieved on average at rank 2 ($MRR@10{\approx}0.50$), and most of the known-items could be identified from the top-10 document lists. In response to ill-defined questions, the known-items were ranked lower by CliniCluster and CQA-1.0, whereas for Google and Google Scholar, significant difference in ranking was not found between well- and ill-defined questions. Less than 40% of the known-items could be identified from the top-10 documents retrieved by CQA-1.0, Google, and Google Scholar. An analysis of the top-ranked documents by strength of evidence revealed that CliniCluster outperformed other search engines by providing a higher number of recent publications with the highest study design. In conclusion, the overall results support the use of CliniCluster in answering therapy questions by ranking highly relevant documents in the top positions of the search results.

• The Journal of the Korea Contents Association
• /
• v.4 no.2
• /
• pp.36-42
• /
• 2004

This paper describes the Korean Question answering system using the syntactic-relation information d verbs to overcome lack of reliable knowledge and linguistic resources. The syntactic-relation information consists d the original form d a verb, usual usage pattern, semantic category of each dependent noun, synonym verbs and passive verbs. We use the syntactic-relation information to parse sentences or phrases with usual usage pattern of the verb and semantic conditions of dependent components on the verb. We also use that information to parse answer candidate sentences, and find an answer from questioned case slot. Our experiments that usage of the syntactic-relation information of verbs to mm lack of reliable knowledge and linguistic resources can be utilized efficiently for the Korean question answering system.

• Journal of the Korean Society for information Management
• /
• v.27 no.2
• /
• pp.21-35
• /
• 2010

The popularity of question answering communities such as Yahoo! Answers and Naver Knowledge-iN and increasing doubts about the competence of lay information providers prompted this study to explore answerers' strategies to provide a credible answer in a question answering community. Forty-four active answerers in Yahoo! Answers were included in this study, and interviews were conducted through email, chat, and over the telephone. This study identified a set of information sources the answerers used, an array of important strategies to provide a credible answer, and their perception of self-claimed expertise. Implications of results were discussed in the context of user instruction.