• Language and Information
• /
• v.18 no.2
• /
• pp.141-168
• /
• 2014

Recognizing spatial information associated with events expressed in natural language text is essential not only for the interpretation of such events and but also for the understanding of the relations among them. However, spatial information is rarely mentioned as compared to events and the association between event and spatial expressions is also highly implicit in a text. This would make it difficult to automate the extraction of spatial information associated with events from the text. In this paper, we give a linguistic analysis of how spatial expressions are associated with event expressions in a text. We first present issues in annotating narrative texts with reference relations between event and spatial expressions, and then discuss surface-level linguistic characteristics of such relations based on the annotated corpus to give a helpful insight into developing an automated recognition method.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.313-319
• /
• 2022

최근 BERT와 같은 트랜스포머 (Transformer) 기반의 모델이 natural language understanding (NLU)와 같은 여러 자연어 처리 태스크에서 좋은 성능을 보인다. 이러한 모델은 여전히 대용량의 학습을 요구한다. 일반적으로, 데이터 증강 기법은 low-resource 환경을 개선하는 데 도움을 준다. 최근 생성 모델을 활용해 합성 데이터를 생성해 데이터를 증강하는 시도가 이루어졌다. 이러한 방법은 원본 문장과 의미론적 유사성을 훼손하지 않으면서 어휘와 구조적 다양성을 높이는 것을 목표로 한다. 본 논문은 task-oriented 한 어휘와 구조를 고려한 데이터 증강 방법을 제안한다. 이를 위해 검색 모델과 사전 학습된 생성 모델을 활용한다. 검색 모델을 사용해 학습 데이터셋의 입력 문장과 유사한 문장 쌍을 검색 (retrieval) 한다. 검색된 유사한 문장 쌍을 사용하여 생성 모델을 학습해 합성 데이터를 생성한다. 본 논문의 방법론은 low-resource 환경에서 베이스라인 성능을 최대 4% 이상 향상할 수 있었으며, 기존의 데이터 증강 방법론보다 높은 성능 향상을 보인다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.461-466
• /
• 2021

본 연구에서는 DECO(Dictionnaire Electronique du COreen) 한국어 전자사전과 LGG(Local-Grammar Graph)에 기반한 반자동 언어데이터 증강(Semi-automatic Symbolic Propagation: SSP) 방식에 입각하여, 핀테크 분야의 CS(Customer Service) 챗봇 NLU(Natural Language Understanding)을 위한 주석 학습 데이터를 효과적으로 생성하고, 이를 기반으로 RASA 오픈 소스에서 제공하는 DIET(Dual Intent and Entity Transformer) 아키텍처를 활용하여 핀테크 CS 챗봇 NLU 시스템을 구현하였다. 실 데이터을 통해 확인된 핀테크 분야의 32가지의 토픽 유형 및 38가지의 핵심 이벤트와 10가지 담화소 구성에 따라, DECO-LGG 데이터 생성 모듈은 질의 및 불만 화행에 대한 양질의 주석 학습 데이터를 효과적으로 생성하며, 이를 의도 분류 및 Slot-filling을 위한 개체명 인식을 종합적으로 처리하는 End to End 방식의 멀티태스크 트랜스포머 모델 DIET로 학습함으로써 DIET-only F1-score 0.931(Intent)/0.865(Slot/Entity), DIET+KoBERT F1-score 0.951(Intent)/0.901(Slot/Entity)의 성능을 확인하였으며, DECO-LGG 기반의 SSP 생성 데이터의 학습 데이터로서의 효과성과 함께 KoBERT에 기반한 DIET 모델 성능의 우수성을 입증하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.44-51
• /
• 1999

This paper presents a massively parallel computational model for the efficient integration of speech and natural language understanding. The phoneme model is based on continuous Hidden Markov Model with context dependent phonemes, and the language model is based on a knowledge base approach. To construct the knowledge base, we adopt a hierarchically-structured semantic network and a memory-based parsing technique that employs parallel marker-passing as an inference mechanism. Our parallel speech recognition algorithm is implemented in a multi-Transputer system using distributed-memory MIMD multiprocessors. Experimental results show that the parallel speech recognition system performs better in recognition accuracy than a word network-based speech recognition system. The recognition accuracy is further improved by applying code-phoneme statistics. Besides, speedup experiments demonstrate the possibility of constructing a realtime parallel speech recognition system.

• Journal of architectural history
• /
• v.19 no.2
• /
• pp.133-152
• /
• 2010

Through the 20th century architectural theory of rational thinking and the principles according to the statement of the firm, Le Corbusier's early works by analyzing the language of architecture, including his architectural concepts and helps the understanding of modern architecture. Masters of modern architecture as a place among the works of Le Corbusier in the 1920s, 'Le Corbusier's White Period' homes to target by age, and that his initial concept of the formation process of clarifying, further the construction of his golden age will be the key to understand. I selected housings from Maison Citrohan to villa Savoye, the category of architectural elements by considering the development process, he examines developments of the concept of modern architectural space. In analysis process, First of all, I am focused on between each element in the development process to review and explicate the integration process. The advent of the machine which he lived, because of its incredible potential reorganization of human society, as well as to celebrate the start of a new lifestyle. His architectural language of the times in the machinism could achieve progress and modern art, which is a new interpretation of the natural world.

• The Journal of Information Systems
• /
• v.21 no.3
• /
• pp.137-161
• /
• 2012

The increasing interest in big data analysis using various data mining techniques indicates that many commercial data mining tools now need to be equipped with fundamental text analysis modules. The most essential prerequisite for accurate analysis of text documents is an understanding of the exact semantics of each term in a document. The main difficulties in understanding the exact semantics of terms are mainly attributable to homonym and synonym problems, which is a traditional problem in the natural language processing field. Some major text mining tools provide a thesaurus to solve these problems, but a thesaurus cannot be used to resolve complex synonym problems. Furthermore, the use of a thesaurus is irrelevant to the issue of homonym problems and hence cannot solve them. In this paper, we propose a semantic text mining methodology that uses ontologies to improve the quality of text mining results by resolving the semantic ambiguity caused by homonym and synonym problems. We evaluate the practical applicability of the proposed methodology by performing a classification analysis to predict customer churn using real transactional data and Q&A articles from the "S" online shopping mall in Korea. The experiments revealed that the prediction model produced by our proposed semantic text mining method outperformed the model produced by traditional text mining in terms of prediction accuracy such as the response, captured response, and lift.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.243-250
• /
• 2020

Knowledge graph-based question answering not only requires deep understanding of the given natural language questions, but it also needs effective reasoning to find the correct answers on a large knowledge graph. In this paper, we propose a deep neural network model for effective reasoning on a knowledge graph, which can find correct answers to complex questions requiring multi-hop inference. The proposed model makes use of highly expressive bilinear graph neural network (BGNN), which can utilize context information between a pair of neighboring nodes, as well as allows bidirectional feature propagation between each entity node and one of its neighboring nodes on a knowledge graph. Performing experiments with an open-domain knowledge base (Freebase) and two natural-language question answering benchmark datasets(WebQuestionsSP and MetaQA), we demonstrate the effectiveness and performance of the proposed model.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1537-1542
• /
• 2017

Emotion plays a key role in both generating and understanding narrative. In this article we analyzed the emotions represented in a movie script based on 8 emotion types from the wheel of emotions by Plutchik. First we conducted manual emotion tagging scene by scene. The most dominant emotions by manual tagging were anger, fear, and surprise. It makes sense when the film script we analyzed is a thriller-genre. We assumed that the emotions around the climax of the story would be heightened as the tension grew up. From manual tagging we could identify three such duration when the tension is high. Next we analyzed the emotions in the same script using Python-based NLTK VADERSentiment tool. The result showed that the emotions of anger and fear were most matched. The emotion of surprise, anticipation, and disgust, however, scored lower matching.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.15-20
• /
• 2023

This paper is a study on the development of an artificial intelligence (AI) system algorithm that recommends indirect advertising products suitable for character web dramas. The goal of this study is to increase viewers' content immersion and help them understand the story of the drama more deeply by recommending indirect advertising products that are suitable for writing lines for web dramas. In this study, we analyze dialogue and plot using the natural language processing model GPT, and develop two types of indirect advertising product recommendation systems, including prop type and background type, based on the analysis results. Through this, products that fit the story of the web drama are appropriately placed, allowing indirect advertisements to be exposed naturally, thereby increasing viewer immersion and enhancing the effectiveness of product promotion. There are limitations of artificial intelligence models, such as the difficulty in fully understanding hidden meanings or cultural nuances, and the difficulty in securing sufficient data for learning. However, this study will provide new insights into how AI can contribute to the production of creative works, and will be an important stepping stone to expand the possibilities of using natural language processing models in the creative industry.

• Korean Journal of Cognitive Science
• /
• v.35 no.1
• /
• pp.23-48
• /
• 2024

Building human-aligned artificial intelligence (AI) for social support remains challenging despite the advancement of Large Language Models. We present a novel method, the Chain of Empathy (CoE) prompting, that utilizes insights from psychotherapy to induce LLMs to reason about human emotional states. This method is inspired by various psychotherapy approaches-Cognitive-Behavioral Therapy (CBT), Dialectical Behavior Therapy (DBT), Person-Centered Therapy (PCT), and Reality Therapy (RT)-each leading to different patterns of interpreting clients' mental states. LLMs without CoE reasoning generated predominantly exploratory responses. However, when LLMs used CoE reasoning, we found a more comprehensive range of empathic responses aligned with each psychotherapy model's different reasoning patterns. For empathic expression classification, the CBT-based CoE resulted in the most balanced classification of empathic expression labels and the text generation of empathic responses. However, regarding emotion reasoning, other approaches like DBT and PCT showed higher performance in emotion reaction classification. We further conducted qualitative analysis and alignment scoring of each prompt-generated output. The findings underscore the importance of understanding the emotional context and how it affects human-AI communication. Our research contributes to understanding how psychotherapy models can be incorporated into LLMs, facilitating the development of context-aware, safe, and empathically responsive AI.