• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.407-411
• /
• 2022

최근 COVID-19로 인해 대중의 의학 분야 관심이 증가하고 있다. 대부분의 의학문서는 전문용어인 의학용어로 구성되어 있어 대중이 이를 보고 이해하기에 어려움이 있다. 의학용어를 쉬운 뜻으로 풀이하는 모델을 이용한다면 대중이 의학 문서를 쉽게 이해할 수 있을 것이다. 이런 문제를 완화하기 위해서 본 논문에서는 Transformer 기반 번역 모델을 이용한 의학용어 탐지 및 해석 모델을 제안한다. 번역 모델에 적용하기 위해 병렬말뭉치가 필요하다. 본 논문에서는 다음과 같은 방법으로 병렬말뭉치를 구축한다: 1) 의학용어 사전을 구축한다. 2) 의학 드라마의 자막으로부터 의학용어를 찾아서 그 뜻풀이로 대체한다. 3) 원자막과 뜻풀이가 포함된 자막을 나란히 배열한다. 구축된 병렬말뭉치를 이용해서 Transformer 번역모델에 적용하여 전문용어를 찾아서 해석하는 모델을 구축한다. 각 문장은 음절 단위로 나뉘어 사전학습 된 KoCharELECTRA를 이용해서 임베딩한다. 제안된 모델은 약 69.3%의 어절단위 BLEU 점수를 보였다. 제안된 의학용어 해석기를 통해 대중이 의학문서를 좀 더 쉽게 접근할 수 있을 것이다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.533-536
• /
• 2019

의존 구문 분석은 문장 구성 성분 간의 의존 관계를 분석하는 태스크로, 자연어 이해의 대표적인 과제 중 하나이다. 본 논문에서는 한국어 의존 구문 분석의 성능 향상을 위해 Deep Bi-Affine Network와 Left to Right Dependency Parser를 적용하고, 새롭게 한국어의 언어적 특징을 반영한 Right to Left Dependency Parser 모델을 제안한다. 3개의 의존 구문 분석 모델에 단어 표현을 생성하는 방법으로 ELMo, BERT 임베딩 방법을 적용하고 여러 종류의 모델을 앙상블하여 세종 의존 구문 분석 데이터에 대해 UAS 94.50, LAS 92.46 성능을 얻을 수 있었다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.603-608
• /
• 2024

Recently, the frequency of computer engineering and technology interviews has increased in the process of hiring developers, and accordingly, the burden of technical interviews among interviewees has also increased. However, during computer engineering technical interview practice, it is difficult to judge whether one's answers are correct, and to measure the appropriate vocalization speed by oneself. In this paper, we propose a computer engineering technical interview support system using similarity measurement technology. The proposed system measures the technical accuracy of the interviewee's answers through a sentence similarity evaluation procedure using cosine similarity to measure the technical accuracy of the interviewee's answers. It also measures the speech rate and provides it to the interviewee.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.144-151
• /
• 2020

In a mobile environment, communication takes place via SMS text messages. Vocabularies used in SMS texts can be expected to use vocabularies of different classes from those used in general Korean literary style sentence. For example, in the case of a typical literary style, the sentence is correctly initiated or terminated and the sentence is well constructed, while SMS text corpus often replaces the component with an omission and a brief representation. To analyze these vocabulary usage characteristics, the existing colloquial style corpus and the literary style corpus are used. The experiment compares and analyzes the vocabulary use characteristics of the colloquial corpus SMS text corpus and the Naver Sentiment Movie Corpus, and the written Korean written corpus. For the comparison and analysis of vocabulary for each corpus, the part of speech tag adjective (VA) was used as a standard, and a distinctive collexeme analysis method was used to measure collostructural strength. As a result, it was confirmed that adjectives related to emotional expression such as'good-','sorry-', and'joy-' were preferred in the SMS text corpus, while adjectives related to evaluation expressions were preferred in the Naver Sentiment Movie Corpus. The word embedding was used to automatically construct a sentiment lexicon based on the extracted adjectives with high collostructural strength, and a total of 343,603 sentiment representations were automatically built.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.195-204
• /
• 2023

In this study, prompt engineering that improves prompts was explored to improve the performance of teaching and learning materials recommendations using generative artificial intelligence such as GPT and Stable Diffusion. Picture materials were used as the types of teaching and learning materials. To explore the impact of the prompt composition, a Zero-Shot prompt, a prompt containing learning target grade information, a prompt containing learning goals, and a prompt containing both learning target grades and learning goals were designed to collect responses. The collected responses were embedded using Sentence Transformers, dimensionalized to t-SNE, and visualized, and then the relationship between prompts and responses was explored. In addition, each response was clustered using the k-means clustering algorithm, then the adjacent value of the widest cluster was selected as a representative value, imaged using Stable Diffusion, and evaluated by 30 elementary school teachers according to the criteria for evaluating teaching and learning materials. Thirty teachers judged that three of the four picture materials recommended were of educational value, and two of them could be used for actual classes. The prompt that recommended the most valuable picture material appeared as a prompt containing both the target grade and the learning goal.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• Smart Media Journal
• /
• v.11 no.10
• /
• pp.89-96
• /
• 2022

An open domain machine reading comprehension is a model that adds a function to search paragraphs as there are no paragraphs related to a given question. Document searches have an issue of lower performance with a lot of documents despite abundant research with word frequency based TF-IDF. Paragraph selections also have an issue of not extracting paragraph contexts, including sentence characteristics accurately despite a lot of research with word-based embedding. Document reading comprehension has an issue of slow learning due to the growing number of parameters despite a lot of research on BERT. Trying to solve these three issues, this study used BM25 which considered even sentence length and InferSent to get sentence contexts, and proposed an open domain machine reading comprehension with ALBERT to reduce the number of parameters. An experiment was conducted with SQuAD1.1 datasets. BM25 recorded a higher performance of document research than TF-IDF by 3.2%. InferSent showed a higher performance in paragraph selection than Transformer by 0.9%. Finally, as the number of paragraphs increased in document comprehension, ALBERT was 0.4% higher in EM and 0.2% higher in F1.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1290-1295
• /
• 2017

Document classification, a task of classifying the category of each document based on text, is one of the fundamental areas for natural language processing. Document classification may be used in various fields such as topic classification and sentiment classification. Neural network models for document classification can be divided into two categories: word-level models and character-level models that treat words and characters as basic units respectively. In this study, we propose a neural network model that combines character-level and word-level models to improve performance of document classification. The proposed model extracts the feature vector of each word by combining information obtained from a word embedding matrix and information encoded by a character-level neural network. Based on feature vectors of words, the model classifies documents with a hierarchical structure wherein recurrent neural networks with attention mechanisms are used for both the word and the sentence levels. Experiments on real life datasets demonstrate effectiveness of our proposed model.