• ETRI Journal
• /
• v.46 no.1
• /
• pp.11-21
• /
• 2024

We focus on open-domain question-answering tasks that involve a chain-of-reasoning, which are primarily implemented using large language models. With an emphasis on cost-effectiveness, we designed EffiChainQA, an architecture centered on the use of small language models. We employed a retrieval-based language model to address the limitations of large language models, such as the hallucination issue and the lack of updated knowledge. To enhance reasoning capabilities, we introduced a question decomposer that leverages a generative language model and serves as a key component in the chain-of-reasoning process. To generate training data for our question decomposer, we leveraged ChatGPT, which is known for its data augmentation ability. Comprehensive experiments were conducted using the HotpotQA dataset. Our method outperformed several established approaches, including the Chain-of-Thoughts approach, which is based on large language models. Moreover, our results are on par with those of state-of-the-art Retrieve-then-Read methods that utilize large language models.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.199-206
• /
• 2021

Rhetorical relations between two text fragments are essential information and support natural language processing applications such as Question - Answering (QA) system and automatic text summarization to produce an effective outcome. Question - Answering (QA) system facilitates users to retrieve a meaningful response. There is a demand for rhetorical relation based datasets to develop such a system to interpret and respond to user requests. There are a limited number of datasets for developing an Arabic QA system. Thus, there is a lack of an effective QA system in the Arabic language. Recent research works reveal that unsupervised learning can support the QA system to reply to users queries. In this study, researchers intend to develop a rhetorical relation based dataset for implementing unsupervised learning applications. A web crawler is developed to crawl Arabic content from the web. A discourse-annotated corpus is generated using the rhetorical structural theory. A Naïve Bayes based QA system is developed to evaluate the performance of datasets. The outcome shows that the performance of the QA system is improved with proposed dataset and able to answer user queries with an appropriate response. In addition, the results on fine-grained and coarse-grained relations reveal that the dataset is highly reliable.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.346-356
• /
• 2022

The jurisprudential legal rules govern the way Muslims react and interact to daily life. This creates a huge stream of questions, that require highly qualified and well-educated individuals, called Muftis. With Muslims representing almost 25% of the planet population, and the scarcity of qualified Muftis, this creates a demand supply problem calling for Automation solutions. This motivates the application of Artificial Intelligence (AI) to solve this problem, which requires a well-designed Question-Answering (QA) system to solve it. In this work, we propose a QA system, based on retrieval augmented generative transformer model for jurisprudential legal question. The main idea in the proposed architecture is the leverage of both state-of-the art transformer models, and the existing knowledge base of legal sources and question-answers. With the sensitivity of the domain in mind, due to its importance in Muslims daily lives, our design balances between exploitation of knowledge bases, and exploration provided by the generative transformer models. We collect a custom data set of 850,000 entries, that includes the question, answer, and category of the question. Our evaluation methodology is based on both quantitative and qualitative methods. We use metrics like BERTScore and METEOR to evaluate the precision and recall of the system. We also provide many qualitative results that show the quality of the generated answers, and how relevant they are to the asked questions.

• Korean Journal of Cognitive Science
• /
• v.2 no.2
• /
• pp.309-339
• /
• 1990

The most common way that people communicate is by speaking or writing natural languages.But if people use computers in the modern technology,they should learn artificial programming languages.If computers could understand what people mean when people speak or type natural languages,people would use the computers more easily and naturally.but there is a problem.The language which people use has vagueness.For example,the convential computer system cant's handle the subjective feeling like 'tall' or 'young'.So peole must specify the exact threshold like 'more'than 25 ages'.We have developed the knowledge-based natural language question answering system which can handle sentences having fuzzy concepts by using blackboard model.Our goal of this research is to develop a portable question answering system as interface for database systems or understanding systems.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.795-802
• /
• 2002

We propose a fast and powerful Question-answering (QA) system in Korean, which uses a predictive answer indexer based on 2-pass scoring method. The indexing process is as follows. The predictive answer indexer first extracts all answer candidates in a document. Then, using 2-pass scoring method, it gives scores to the adjacent content words that are closely related with each answer candidate. Next, it stores the weighted content words with each candidate into a database. Using this technique, along with a complementary analysis of questions which is based on lexico-syntactic pattern matching method, the proposed QA system saves response time and enhances the precision.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1643-1652
• /
• 2022

Most of the existing machine reading research has used Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) algorithms as networks. Among them, RNN was slow in training, and Question Answering Network (QANet) was announced to improve training speed. QANet is a model composed of CNN and self-attention. CNN extracts semantic and syntactic information well from the local corpus, but there is a limit to extracting the corresponding information from the global corpus. Graph Convolutional Networks (GCN) extracts semantic and syntactic information relatively well from the global corpus. In this paper, to take advantage of this strength of GCN, we propose I-QANet, which changed the CNN of QANet to GCN. The proposed model performed 1.2 times faster than the baseline in the Stanford Question Answering Dataset (SQuAD) dataset and showed 0.2% higher performance in Exact Match (EM) and 0.7% higher in F1. Furthermore, in the Korean Question Answering Dataset (KorQuAD) dataset consisting only of Korean, the learning time was 1.1 times faster than the baseline, and the EM and F1 performance were also 0.9% and 0.7% higher, respectively.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.116-121
• /
• 2017

cQA(Community-based Question Answering) 시스템은 온라인 커뮤니티를 통해 사용자들이 질문을 남기고 답변을 작성할 수 있도록 만들어진 시스템이다. 신규 질문이 인입되면, 기존에 축적된 cQA 저장소에서 해당 질문과 가장 유사한 질문을 검색하고, 그 질문에 대한 답변을 신규 질문에 대한 답변으로 대체할 수 있다. 하지만, 키워드 매칭을 사용하는 전통적인 검색 방식으로는 문장에 내재된 의미들을 이용할 수 없다는 한계가 있다. 이를 극복하기 위해서는 의미적으로 동일한 문장들로 학습이 되어야 하지만, 이러한 데이터를 대량으로 확보하기에는 어려움이 있다. 본 논문에서는 질문이 제목과 내용으로 분리되어 있는 대량의 cQA 셋에서, 질문 제목과 내용을 의미 벡터 공간으로 사상하고 두 벡터의 상대적 거리가 가깝게 되도록 학습함으로써 의사(pseudo) 유사 의미의 성질을 내재화 하였다. 또한, 질문 제목과 내용의 의미 벡터 표현(representation)을 위하여, semi-training word embedding과 CNN(Convolutional Neural Network)을 이용한 딥러닝 기법을 제안하였다. 유사 질문 검색 실험 결과, 제안 모델을 이용한 검색이 키워드 매칭 기반 검색보다 좋은 성능을 보였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.1
• /
• pp.1-8
• /
• 2007

When confronted with a query, question answering systems endeavor to extract the most exact answers possible by determining the answer type that fits with the key terms used in the query. However, the efficacy of such systems is limited by the fact that the terms used in a query may be in a syntactic form different to that of the same words in a document. In this paper, we present an efficient semantic query expansion methodology based on query patterns in a question category concept list comprised of terms that are semantically close to terms used in a query. The proposed system first constructs a concept list for each question type and then builds the concept list for each question category using a learning algorithm. The results of the present experiments suggest the promise of the proposed method.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.771-781
• /
• 2019

We propose the VS³-NET model to solve the task of question answering questions with machine-reading comprehension that searches for an appropriate answer in a given context. VS³-NET is a model that trains latent variables for each question using variational inferences based on a model of a simple recurrent unit-based sentences and self-matching networks. The types of questions vary, and the answers depend on the type of question. To perform efficient inference and learning, we introduce neural question-type models to approximate the prior and posterior distributions of the latent variables, and we use these approximated distributions to optimize a reparameterized variational lower bound. The context given in machine-reading comprehension usually comprises several sentences, leading to performance degradation caused by context length. Therefore, we model a hierarchical structure using sentence encoding, in which as the context becomes longer, the performance degrades. Experimental results show that the proposed VS³-NET model has an exact-match score of 76.8% and an F1 score of 84.5% on the SQuAD test set.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.466-475
• /
• 2003

To build an efficient Question-Answering (QA) system, a question type classifier is needed. It can classify user's queries into predefined categories regardless of the surface form of a question. In this paper, we propose a question type classifier using a Support Vector Machine (SVM). The question type classifier first extracts features like lexical forms, part of speech and semantic markers from a user's question. The system uses $X^2$ statistic to select important features. Selected features are represented as a vector. Finally, a SVM categorizes questions into predefined categories according to the extracted features. In the experiment, the proposed system accomplished 86.4% accuracy The system precisely classifies question type without using any rules like lexico-syntactic patterns. Therefore, the system is robust and easily portable to other domains.