• ETRI Journal
• /
• 제45권1호
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.281-291
• /
• 2021

The Islamic jurisprudential legal system represents an essential component of the Islamic religion, that governs many aspects of Muslims' daily lives. This creates many questions that require interpretations by qualified specialists, or Muftis according to the main sources of legislation in Islam. The Islamic jurisprudence is usually classified into branches, according to which the questions can be categorized and classified. Such categorization has many applications in automated question-answering systems, and in manual systems in routing the questions to a specialized Mufti to answer specific topics. In this work we tackle the problem of automatic categorisation of Islamic jurisprudential legal questions using deep learning techniques. In this paper, we build a hierarchical deep learning model that first extracts the question text features at two levels: word and sentence representation, followed by a text classifier that acts upon the question representation. To evaluate our model, we build and release the largest publicly available dataset of Islamic questions and answers, along with their topics, for 52 topic categories. We evaluate different state-of-the art deep learning models, both for word and sentence embeddings, comparing recurrent and transformer-based techniques, and performing extensive ablation studies to show the effect of each model choice. Our hierarchical model is based on pre-trained models, taking advantage of the recent advancement of transfer learning techniques, focused on Arabic language.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권6호
• /
• pp.235-242
• /
• 2021

본 연구에서는 포인터 네트워크 모델을 의존 구문 분석에 맞게 확장한 스택-포인터 네트워크 모델을 이용하여 한국어 의존 구문 분석기를 구현한다. 스택-포인터 네트워크 모델 기반 의존 구문 분석기는 인코더-디코더로 구성되어 있으며 다른 의존 구문 분석기와 달리 내부 스택을 갖고 있어 루트부터 시작하는 하향식 구문 분석이 가능하다. 디코더의 각 단계에서는 의존소를 찾기 위해 부모 노드뿐만 아니라 이미 파생된 트리 구조에서 조부모와 형제 노드를 참조할 수 있다. 기존 연구에서는 단순하게 해당 노드들의 합을 계산하여 입력으로 사용하였고, 형제 노드의 경우에는 가장 최근에 방문했던 것만을 사용할 수 있었다. 본 연구에서는 그래프 어텐션 네트워크를 도입하여 이미 파생된 부분 트리를 표현하고 이를 스택-포인터 네트워크의 입력으로 사용하도록 구문 분석기를 수정한다. 세종 코퍼스와 모두의 코퍼스를 대상을 실험한 결과 레이어 2의 그래프 어텐션 네트워크를 이용하여 부분 트리를 표현했을 때 특히 문장 단위의 구문 분석 정확도에서 많은 성능 향상을 확인할 수 있었다.