• Title/Summary/Keyword: language training

Search Result 689, Processing Time 0.022 seconds

Urdu News Classification using Application of Machine Learning Algorithms on News Headline

  • Khan, Muhammad Badruddin
    • International Journal of Computer Science & Network Security
    • /
    • v.21 no.2
    • /
    • pp.229-237
    • /
    • 2021
  • Our modern 'information-hungry' age demands delivery of information at unprecedented fast rates. Timely delivery of noteworthy information about recent events can help people from different segments of life in number of ways. As world has become global village, the flow of news in terms of volume and speed demands involvement of machines to help humans to handle the enormous data. News are presented to public in forms of video, audio, image and text. News text available on internet is a source of knowledge for billions of internet users. Urdu language is spoken and understood by millions of people from Indian subcontinent. Availability of online Urdu news enable this branch of humanity to improve their understandings of the world and make their decisions. This paper uses available online Urdu news data to train machines to automatically categorize provided news. Various machine learning algorithms were used on news headline for training purpose and the results demonstrate that Bernoulli Naïve Bayes (Bernoulli NB) and Multinomial Naïve Bayes (Multinomial NB) algorithm outperformed other algorithms in terms of all performance parameters. The maximum level of accuracy achieved for the dataset was 94.278% by multinomial NB classifier followed by Bernoulli NB classifier with accuracy of 94.274% when Urdu stop words were removed from dataset. The results suggest that short text of headlines of news can be used as an input for text categorization process.

The Effect of Communication of Service Employee on Customer Satisfaction, and Reuse Intention

  • SUNG, Yu-Lim;PARK, Hye-Yoon
    • The Journal of Economics, Marketing and Management
    • /
    • v.9 no.2
    • /
    • pp.21-31
    • /
    • 2021
  • Purpose: This study aims to provide marketing implications for training and face-to-face service employee communication by analyzing how communication by Korean crews at foreign airlines affects passengers' perception and how this perception relates to airline service quality and customer satisfaction. Research design, data: The collection of questionnaires for the demonstration in this study has collected 300 questionnaires for about a month for Korean passengers who are aware of the presence of Korean crew on board aircraft. Results: The study analyzed the relationship between the communication ability, customer satisfaction, and reuse intention of foreign airlines. An empirical analysis of the relationship between quality of airline service, customer satisfaction, and intention of re-use can suggest the following implications based on the language and non-verbal communication capabilities of the Korean crew working for foreign airlines. Conclusions: We studied the impact of communication between Korean crews working for foreign airlines on the quality of airline service, customer satisfaction and reuse intention. The Korean crew should also work for overseas airlines and consider communication as important and expand their overall foreign language education and communication skills to have a positive impact on not only Korean passengers but also their own citizens.

Development of Tourism Information Named Entity Recognition Datasets for the Fine-tune KoBERT-CRF Model

  • Jwa, Myeong-Cheol;Jwa, Jeong-Woo
    • International Journal of Internet, Broadcasting and Communication
    • /
    • v.14 no.2
    • /
    • pp.55-62
    • /
    • 2022
  • A smart tourism chatbot is needed as a user interface to efficiently provide smart tourism services such as recommended travel products, tourist information, my travel itinerary, and tour guide service to tourists. We have been developed a smart tourism app and a smart tourism information system that provide smart tourism services to tourists. We also developed a smart tourism chatbot service consisting of khaiii morpheme analyzer, rule-based intention classification, and tourism information knowledge base using Neo4j graph database. In this paper, we develop the Korean and English smart tourism Name Entity (NE) datasets required for the development of the NER model using the pre-trained language models (PLMs) for the smart tourism chatbot system. We create the tourism information NER datasets by collecting source data through smart tourism app, visitJeju web of Jeju Tourism Organization (JTO), and web search, and preprocessing it using Korean and English tourism information Name Entity dictionaries. We perform training on the KoBERT-CRF NER model using the developed Korean and English tourism information NER datasets. The weight-averaged precision, recall, and f1 scores are 0.94, 0.92 and 0.94 on Korean and English tourism information NER datasets.

A Multi-task Self-attention Model Using Pre-trained Language Models on Universal Dependency Annotations

  • Kim, Euhee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.11
    • /
    • pp.39-46
    • /
    • 2022
  • In this paper, we propose a multi-task model that can simultaneously predict general-purpose tasks such as part-of-speech tagging, lemmatization, and dependency parsing using the UD Korean Kaist v2.3 corpus. The proposed model thus applies the self-attention technique of the BERT model and the graph-based Biaffine attention technique by fine-tuning the multilingual BERT and the two Korean-specific BERTs such as KR-BERT and KoBERT. The performances of the proposed model are compared and analyzed using the multilingual version of BERT and the two Korean-specific BERT language models.

SimKoR: A Sentence Similarity Dataset based on Korean Review Data and Its Application to Contrastive Learning for NLP (SimKoR: 한국어 리뷰 데이터를 활용한 문장 유사도 데이터셋 제안 및 대조학습에서의 활용 방안 )

  • Jaemin Kim;Yohan Na;Kangmin Kim;Sang Rak Lee;Dong-Kyu Chae
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.245-248
    • /
    • 2022
  • 최근 자연어 처리 분야에서 문맥적 의미를 반영하기 위한 대조학습 (contrastive learning) 에 대한 연구가 활발히 이뤄지고 있다. 이 때 대조학습을 위한 양질의 학습 (training) 데이터와 검증 (validation) 데이터를 이용하는 것이 중요하다. 그러나 한국어의 경우 대다수의 데이터셋이 영어로 된 데이터를 한국어로 기계 번역하여 검토 후 제공되는 데이터셋 밖에 존재하지 않는다. 이는 기계번역의 성능에 의존하는 단점을 갖고 있다. 본 논문에서는 한국어 리뷰 데이터로 임베딩의 의미 반영 정도를 측정할 수 있는 간단한 검증 데이터셋 구축 방법을 제안하고, 이를 활용한 데이터셋인 SimKoR (Similarity Korean Review dataset) 을 제안한다. 제안하는 검증 데이터셋을 이용해서 대조학습을 수행하고 효과성을 보인다.

  • PDF

Sentence Unit De-noising Training Method for Korean Grammar Error Correction Model (한국어 문법 오류 교정 모델을 위한 문장 단위 디노이징 학습법)

  • Hoonrae Kim;Yunsu Kim;Gary Geunbae Lee
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.507-511
    • /
    • 2022
  • 문법 교정 모델은 입력된 텍스트에 존재하는 문법 오류를 탐지하여 이를 문법적으로 옳게 고치는 작업을 수행하며, 학습자에게 더 나은 학습 경험을 제공하기 위해 높은 정확도와 재현율을 필요로 한다. 이를 위해 최근 연구에서는 문단 단위 사전 학습을 완료한 모델을 맞춤법 교정 데이터셋으로 미세 조정하여 사용한다. 하지만 본 연구에서는 기존 사전 학습 방법이 문법 교정에 적합하지 않다고 판단하여 문단 단위 데이터셋을 문장 단위로 나눈 뒤 각 문장에 G2P 노이즈와 편집거리 기반 노이즈를 추가한 데이터셋을 제작하였다. 그리고 문단 단위 사전 학습한 모델에 해당 데이터셋으로 문장 단위 디노이징 사전 학습을 추가했고, 그 결과 성능이 향상되었다. 노이즈 없이 문장 단위로 분할된 데이터셋을 사용하여 디노이징 사전 학습한 모델을 통해 문장 단위 분할의 효과를 검증하고자 했고, 디노이징 사전 학습하지 않은 기존 모델보다 성능이 향상되는 것을 확인하였다. 또한 둘 중 하나의 노이즈만을 사용하여 디노이징 사전 학습한 두 모델의 성능이 큰 차이를 보이지 않는 것을 통해 인공적인 무작위 편집거리 노이즈만을 사용한 모델이 언어학적 지식이 필요한 G2P 노이즈만을 사용한 모델에 필적하는 성능을 보일 수 있다는 것을 확인할 수 있었다.

  • PDF

TOEIC Model Training Through Template-Based Fine-Tuning (템플릿 기반 미세조정을 통한 토익 모델 훈련)

  • Jeongwoo Lee;Hyeonseok Moon;Kinam Park;Heuiseok Lim
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.324-328
    • /
    • 2022
  • 기계 독해란 주어진 문서를 이해하고 문서 내의 내용에 대한 질문에 답을 추론하는 연구 분야이며, 기계 독해 문제의 종류 중에는 여러 개의 선택지에서 질문에 대한 답을 선택하는 객관식 형태의 문제가 존재한다. 이러한 자연어 처리 문제를 해결하기 위해 기존 연구에서는 사전학습된 언어 모델을 미세조정하여 사용하는 방법이 널리 활용되고 있으나, 학습 데이터가 부족한 환경에서는 기존의 일반적인 미세조정 방법으로 모델의 성능을 높이는 것이 제한적이며 사전학습된 의미론적인 정보를 충분히 활용하지 못하여 성능 향상에 한계가 있다. 이에 본 연구에서는 기존의 일반적인 미세조정 방법에 템플릿을 적용한 템플릿 기반 미세조정 방법을 통해 사전학습된 의미론적인 정보를 더욱 활용할 수 있도록 한다. 객관식 형태의 기계 독해 문제 중 하나인 토익 문제에 대해 모델을 템플릿 기반 미세조정 방법으로 실험을 진행하여 템플릿이 모델 학습에 어떠한 영향을 주는지 확인하였다.

  • PDF

Improved Character-Based Neural Network for POS Tagging on Morphologically Rich Languages

  • Samat Ali;Alim Murat
    • Journal of Information Processing Systems
    • /
    • v.19 no.3
    • /
    • pp.355-369
    • /
    • 2023
  • Since the widespread adoption of deep-learning and related distributed representation, there have been substantial advancements in part-of-speech (POS) tagging for many languages. When training word representations, morphology and shape are typically ignored, as these representations rely primarily on collecting syntactic and semantic aspects of words. However, for tasks like POS tagging, notably in morphologically rich and resource-limited language environments, the intra-word information is essential. In this study, we introduce a deep neural network (DNN) for POS tagging that learns character-level word representations and combines them with general word representations. Using the proposed approach and omitting hand-crafted features, we achieve 90.47%, 80.16%, and 79.32% accuracy on our own dataset for three morphologically rich languages: Uyghur, Uzbek, and Kyrgyz. The experimental results reveal that the presented character-based strategy greatly improves POS tagging performance for several morphologically rich languages (MRL) where character information is significant. Furthermore, when compared to the previously reported state-of-the-art POS tagging results for Turkish on the METU Turkish Treebank dataset, the proposed approach improved on the prior work slightly. As a result, the experimental results indicate that character-based representations outperform word-level representations for MRL performance. Our technique is also robust towards the-out-of-vocabulary issues and performs better on manually edited text.

Model Training and Data Augmentation Schemes For the High-level Machine Reading Comprehension (고차원 기계 독해를 위한 모델 훈련 및 데이터 증강 방안)

  • Lee, Jeongwoo;Moon, Hyeonseok;Park, Chanjun;Lim, Heuiseok
    • Annual Conference on Human and Language Technology
    • /
    • 2021.10a
    • /
    • pp.47-52
    • /
    • 2021
  • 최근 지문을 바탕으로 답을 추론하는 연구들이 많이 이루어지고 있으며, 대표적으로 기계 독해 연구가 존재하고 관련 데이터 셋 또한 여러 가지가 공개되어 있다. 그러나 한국의 대학수학능력시험 국어 영역과 같은 복잡한 구조의 문제에 대한 고차원적인 문제 해결 능력을 요구하는 데이터 셋은 거의 존재하지 않는다. 이로 인해 고차원적인 독해 문제를 해결하기 위한 연구가 활발히 이루어지고 있지 않으며, 인공지능 모델의 독해 능력에 대한 성능 향상이 제한적이다. 기존의 입력 구조가 단조로운 독해 문제에 대한 모델로는 복잡한 구조의 독해 문제에 적용하기가 쉽지 않으며, 이를 해결하기 위해서는 새로운 모델 훈련 방법이 필요하다. 이에 복잡한 구조의 고차원적인 독해 문제에도 대응이 가능하도록 하는 모델 훈련 방법을 제안하고자 한다. 더불어 3가지의 데이터 증강 기법을 제안함으로써 고차원 독해 문제 데이터 셋의 부족 문제 또한 해소하고자 한다.

  • PDF

Chinese Multi-domain Task-oriented Dialogue System based on Paddle (Paddle 기반의 중국어 Multi-domain Task-oriented 대화 시스템)

  • Deng, Yuchen;Joe, Inwhee
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2022.11a
    • /
    • pp.308-310
    • /
    • 2022
  • With the rise of the Al wave, task-oriented dialogue systems have become one of the popular research directions in academia and industry. Currently, task-oriented dialogue systems mainly adopt pipelined form, which mainly includes natural language understanding, dialogue state decision making, dialogue state tracking and natural language generation. However, pipelining is prone to error propagation, so many task-oriented dialogue systems in the market are only for single-round dialogues. Usually single- domain dialogues have relatively accurate semantic understanding, while they tend to perform poorly on multi-domain, multi-round dialogue datasets. To solve these issues, we developed a paddle-based multi-domain task-oriented Chinese dialogue system. It is based on NEZHA-base pre-training model and CrossWOZ dataset, and uses intention recognition module, dichotomous slot recognition module and NER recognition module to do DST and generate replies based on rules. Experiments show that the dialogue system not only makes good use of the context, but also effectively addresses long-term dependencies. In our approach, the DST of dialogue tracking state is improved, and our DST can identify multiple slotted key-value pairs involved in the discourse, which eliminates the need for manual tagging and thus greatly saves manpower.