• 한국전자거래학회지
• /
• 제26권3호
• /
• pp.119-132
• /
• 2021

내용적 연관성에 기반한 연관지식의 파악은 핵심 지식에 대한 서비스와 보안의 기본적인 기능이다. 본 연구는 내용적 연관성을 기준으로 연관지식을 파악하는 기존의 방식, 즉 키워드 기반 방식과 워드임베딩 방식의 연관문서 네트워크 구성 성능을 비교하여 어떤 방식이 정량적/정성적 측면에서 우월한 성능을 나타내는가를 검토한다. 검토 결과 키워드 기반 방식은 핵심 문서 파악 능력과 시맨틱 정보 표현 능력 면에서 우월한 성능을, 워드임베딩 방식은 F1-Score와 Accuracy, 연관성 강도 표현 능력, 대량 문서 처리 능력 면에서 우월한 성능을 나타냈다. 본 연구의 결과는 기업과 사용자의 요구를 반영하여 보다 현실적인 연관지식 서비스 관리에 활용될 수 있다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제22권7호
• /
• pp.315-319
• /
• 2016

음성인식 성능 개선을 위한 언어모델의 기술적 진보는 최근 심층 신경망을 기반으로 한 접근방법으로 한 단계 더 진보한 모양새다. 그러나 연구되고 있는 심층 신경망 기반 언어모델은 대부분 음성인식 이후 리스코링 단계에서 적용할 수 있는 한계를 지닌다. 또한 대규모 어휘에 대한 심층 신경망 접근방법은 아직 시간이 필요하다고 본다. 따라서 본 논문은 심층 신경망 언어 모델의 단순화된 형태인 워드 임베딩 기술을 음성인식 후처리가 아닌 기반 N-gram모델에 바로 적용할 수 있는 접근 방법을 찾는다. 클래스 언어모델이 한 접근 방법이 될 수 있는데, 본 연구에서는 워드 임베딩을 우선 구축하고, 해당 어휘별 벡터 정보를 클러스터링하여 클래스 언어모델을 구축 방법을 제시한다. 이를 기존 어휘기반 N-gram 모델에 통합한 후, 언어모델의 성능 개선 여부를 확인한다. 클래스 언어모델의 타당성 검증을 위해 다양한 클래스 개수의 언어모델 실험과 RNN LM과의 비교 결과를 검토한 후, 모든 언어모델의 성능 개선을 보장하는 품사 부착 언어모델 생성 방법을 제안한다.

• Journal of Multimedia Information System
• /
• 제9권2호
• /
• pp.93-102
• /
• 2022

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

• 지능정보연구
• /
• 제25권3호
• /
• pp.19-41
• /
• 2019

텍스트 데이터에 대한 다양한 분석을 위해 최근 비정형 텍스트 데이터를 구조화하는 방안에 대한 연구가 활발하게 이루어지고 있다. doc2Vec으로 대표되는 기존 문서 임베딩 방법은 문서가 포함한 모든 단어를 사용하여 벡터를 만들기 때문에, 문서 벡터가 핵심 단어뿐 아니라 주변 단어의 영향도 함께 받는다는 한계가 있다. 또한 기존 문서 임베딩 방법은 하나의 문서가 하나의 벡터로 표현되기 때문에, 다양한 주제를 복합적으로 갖는 복합 문서를 정확하게 사상하기 어렵다는 한계를 갖는다. 본 논문에서는 기존의 문서 임베딩이 갖는 이러한 두 가지 한계를 극복하기 위해 다중 벡터 문서 임베딩 방법론을 새롭게 제안한다. 구체적으로 제안 방법론은 전체 단어가 아닌 핵심 단어만 이용하여 문서를 벡터화하고, 문서가 포함하는 다양한 주제를 분해하여 하나의 문서를 여러 벡터의 집합으로 표현한다. KISS에서 수집한 총 3,147개의 논문에 대한 실험을 통해 복합 문서를 단일 벡터로 표현하는 경우의 벡터 왜곡 현상을 확인하였으며, 복합 문서를 의미적으로 분해하여 다중 벡터로 나타내는 제안 방법론에 의해 이러한 왜곡 현상을 보정하고 각 문서를 더욱 정확하게 임베딩할 수 있음을 확인하였다.

• ETRI Journal
• /
• 제44권3호
• /
• pp.413-425
• /
• 2022

The study of literary texts is one of the earliest disciplines practiced around the globe. Poetry is artistic writing in which words are carefully chosen and arranged for their meaning, sound, and rhythm. Poetry usually has a broad and profound sense that makes it difficult to be interpreted even by humans. The essence of poetry is Rasa, which signifies mood or emotion. In this paper, we propose a poetry classification-based approach to automatically extract similar poems from a repository. Specifically, we perform a novel Rasa-based classification of Hindi poetry. For the task, we primarily used lexical features in a bag-of-words model trained using the support vector machine classifier. In the model, we employed Hindi WordNet, Latent Semantic Indexing, and Word2Vec-based neural word embedding. To extract the rich feature vectors, we prepared a repository containing 37 717 poems collected from various sources. We evaluated the performance of the system on a manually constructed dataset containing 945 Hindi poems. Experimental results demonstrated that the proposed model attained satisfactory performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.652-657
• /
• 2018

With the rapid development of e-commerce, many customers can now express their opinion on various kinds of product at discussion groups, merchant sites, social networks, etc. Discerning a consensus opinion about a product sold online is difficult due to more and more reviews become available on the internet. Opinion Mining, also known as Sentiment analysis, is the task of automatically detecting and understanding the sentimental expressions about a product from customer textual reviews. Recently, researchers have proposed various approaches for evaluation in sentiment mining by applying several techniques for document, sentence and aspect level. Aspect-based sentiment analysis is getting widely interesting of researchers; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces an approach of knowledge representation for the task of analyzing product aspect rating. We focus on how to form the nature of sentiment representation from textual opinion by utilizing the representation learning methods which include word embedding and compositional vector models. Our experiment is performed on a dataset of reviews from electronic domain and the obtained result show that the proposed system achieved outstanding methods in previous studies.

• ETRI Journal
• /
• 제42권1호
• /
• pp.90-100
• /
• 2020

Named entity recognition (NER) continues to be an important task in natural language processing because it is featured as a subtask and/or subproblem in information extraction and machine translation. In Urdu language processing, it is a very difficult task. This paper proposes various deep recurrent neural network (DRNN) learning models with word embedding. Experimental results demonstrate that they improve upon current state-of-the-art NER approaches for Urdu. The DRRN models evaluated include forward and bidirectional extensions of the long short-term memory and back propagation through time approaches. The proposed models consider both language-dependent features, such as part-of-speech tags, and language-independent features, such as the "context windows" of words. The effectiveness of the DRNN models with word embedding for NER in Urdu is demonstrated using three datasets. The results reveal that the proposed approach significantly outperforms previous conditional random field and artificial neural network approaches. The best f-measure values achieved on the three benchmark datasets using the proposed deep learning approaches are 81.1%, 79.94%, and 63.21%, respectively.

• International Journal of Advanced Culture Technology
• /
• 제5권1호
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• ETRI Journal
• /
• 제46권1호
• /
• pp.35-47
• /
• 2024

This study introduces CR-M-SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding-based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost-effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR-M-SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high-recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.