• Title, Summary, Keyword: machine reading comprehension

Search Result 17, Processing Time 0.043 seconds

S2-Net: Machine reading comprehension with SRU-based self-matching networks

  • Park, Cheoneum;Lee, Changki;Hong, Lynn;Hwang, Yigyu;Yoo, Taejoon;Jang, Jaeyong;Hong, Yunki;Bae, Kyung-Hoon;Kim, Hyun-Ki
    • ETRI Journal
    • /
    • v.41 no.3
    • /
    • pp.371-382
    • /
    • 2019
  • Machine reading comprehension is the task of understanding a given context and finding the correct response in that context. A simple recurrent unit (SRU) is a model that solves the vanishing gradient problem in a recurrent neural network (RNN) using a neural gate, such as a gated recurrent unit (GRU) and long short-term memory (LSTM); moreover, it removes the previous hidden state from the input gate to improve the speed compared to GRU and LSTM. A self-matching network, used in R-Net, can have a similar effect to coreference resolution because the self-matching network can obtain context information of a similar meaning by calculating the attention weight for its own RNN sequence. In this paper, we construct a dataset for Korean machine reading comprehension and propose an $S^2-Net$ model that adds a self-matching layer to an encoder RNN using multilayer SRU. The experimental results show that the proposed $S^2-Net$ model has performance of single 68.82% EM and 81.25% F1, and ensemble 70.81% EM, 82.48% F1 in the Korean machine reading comprehension test dataset, and has single 71.30% EM and 80.37% F1 and ensemble 73.29% EM and 81.54% F1 performance in the SQuAD dev dataset.

Machine Reading Comprehension-based Question and Answering System for Search and Analysis of Safety Standards (안전기준의 검색과 분석을 위한 기계독해 기반 질의응답 시스템)

  • Kim, Minho;Cho, Sanghyun;Park, Dugkeun;Kwon, Hyuk-Chul
    • Journal of Korea Multimedia Society
    • /
    • v.23 no.2
    • /
    • pp.351-360
    • /
    • 2020
  • If various unreasonable safety standards are preemptively and effectively readjusted, the risk of accidents can be reduced. In this paper, we proposed a machine reading comprehension-based safety standard Q&A system to secure supporting technology for effective search and analysis of safety standards for integrated and systematic management of safety standards. The proposed model finds documents related to safety standard questions in the various laws and regulations, and then divides these documents into provisions. Only those provisions that are likely to contain the answer to the question are selected, and then the BERT-based machine reading comprehension model is used to find answers to questions related to safety standards. When the proposed safety standard Q&A system is applied to KorQuAD dataset, the performance of EM 40.42% and F1 55.34% are shown.

VS3-NET: Neural variational inference model for machine-reading comprehension

  • Park, Cheoneum;Lee, Changki;Song, Heejun
    • ETRI Journal
    • /
    • v.41 no.6
    • /
    • pp.771-781
    • /
    • 2019
  • We propose the VS3-NET model to solve the task of question answering questions with machine-reading comprehension that searches for an appropriate answer in a given context. VS3-NET is a model that trains latent variables for each question using variational inferences based on a model of a simple recurrent unit-based sentences and self-matching networks. The types of questions vary, and the answers depend on the type of question. To perform efficient inference and learning, we introduce neural question-type models to approximate the prior and posterior distributions of the latent variables, and we use these approximated distributions to optimize a reparameterized variational lower bound. The context given in machine-reading comprehension usually comprises several sentences, leading to performance degradation caused by context length. Therefore, we model a hierarchical structure using sentence encoding, in which as the context becomes longer, the performance degrades. Experimental results show that the proposed VS3-NET model has an exact-match score of 76.8% and an F1 score of 84.5% on the SQuAD test set.

Korean Machine Reading Comprehension for Patent Consultation Using BERT (BERT를 이용한 한국어 특허상담 기계독해)

  • Min, Jae-Ok;Park, Jin-Woo;Jo, Yu-Jeong;Lee, Bong-Gun
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.9 no.4
    • /
    • pp.145-152
    • /
    • 2020
  • MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.

S2-Net: Korean Machine Reading Comprehension with SRU-based Self-matching Network (S2-Net: SRU 기반 Self-matching Network를 이용한 한국어 기계 독해)

  • Park, Cheoneum;Lee, Changki;Hong, Sulyn;Hwang, Yigyu;Yoo, Taejoon;Kim, Hyunki
    • 한국어정보학회:학술대회논문집
    • /
    • /
    • pp.35-40
    • /
    • 2017
  • 기계 독해(Machine reading comprehension)는 주어진 문맥을 이해하고, 질문에 적합한 답을 문맥 내에서 찾는 문제이다. Simple Recurrent Unit (SRU)은 Gated Recurrent Unit (GRU)등과 같이 neural gate를 이용하여 Recurrent Neural Network (RNN)에서 발생하는 vanishing gradient problem을 해결하고, gate 입력에서 이전 hidden state를 제거하여 GRU보다 속도를 향상시킨 모델이며, Self-matching Network는 R-Net 모델에서 사용된 것으로, 자기 자신의 RNN sequence에 대하여 어텐션 가중치 (attention weight)를 계산하여 비슷한 의미 문맥 정보를 볼 수 있기 때문에 상호참조해결과 유사한 효과를 볼 수 있다. 본 논문에서는 한국어 기계 독해 데이터 셋을 구축하고, 여러 층의 SRU를 이용한 Encoder에 Self-matching layer를 추가한 $S^2$-Net 모델을 제안한다. 실험 결과, 본 논문에서 제안한 $S^2$-Net 모델이 한국어 기계 독해 데이터 셋에서 EM 65.84%, F1 78.98%의 성능을 보였다.

  • PDF

Korean Machine Reading Comprehension for Patent Consultation using BERT (BERT를 이용한 한국어 특허상담 기계독해)

  • Min, Jae-Ok;Park, Jin-Woo;Jo, Yu-Jeong;Lee, Bong-Gun;Hwang, Kwang-Su;Park, So-Hee
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • /
    • pp.767-769
    • /
    • 2019
  • 기계독해는(Machine reading comprehension) 사용자 질의에 대한 답변이 될 수 있는 내용을 기계가 문서를 이해하여 추론하는 것을 말하며 기계독해를 이용해서 챗봇과 같은 자동상담 서비스에 활용할 수 있다. 최근 자연어처리 분야에서 많은 성능 향상을 보이고 있는 BERT모델을 기계독해 분야에 적용 할 수 있다. 본 논문에서는 특허상담 분야에서 기계독해 task 성능 향상을 위해 특허상담 코퍼스를 사용하여 사전학습(Pre-training)한 BERT모델과 특허상담 기계학습에 적합한 언어처리 기법을 추가하여 성능을 올릴 수 있는 방안을 제안하였고, 본 논문에서 제안한 방법을 사용하여 특허상담 질의에 대한 답변 결정에서 성능이 향상됨을 보였다.

S2-Net: Korean Machine Reading Comprehension with SRU-based Self-matching Network (S2-Net: SRU 기반 Self-matching Network를 이용한 한국어 기계 독해)

  • Park, Cheoneum;Lee, Changki;Hong, Sulyn;Hwang, Yigyu;Yoo, Taejoon;Kim, Hyunki
    • Annual Conference on Human and Language Technology
    • /
    • /
    • pp.35-40
    • /
    • 2017
  • 기계 독해(Machine reading comprehension)는 주어진 문맥을 이해하고, 질문에 적합한 답을 문맥 내에서 찾는 문제이다. Simple Recurrent Unit (SRU)은 Gated Recurrent Unit (GRU)등과 같이 neural gate를 이용하여 Recurrent Neural Network (RNN)에서 발생하는 vanishing gradient problem을 해결하고, gate 입력에서 이전 hidden state를 제거하여 GRU보다 속도를 향상시킨 모델이며, Self-matching Network는 R-Net 모델에서 사용된 것으로, 자기 자신의 RNN sequence에 대하여 어텐션 가중치 (attention weight)를 계산하여 비슷한 의미 문맥 정보를 볼 수 있기 때문에 상호참조해결과 유사한 효과를 볼 수 있다. 본 논문에서는 한국어 기계 독해 데이터 셋을 구축하고, 여러 층의 SRU를 이용한 Encoder에 Self-matching layer를 추가한 $S^2$-Net 모델을 제안한다. 실험 결과, 본 논문에서 제안한 $S^2$-Net 모델이 한국어 기계 독해 데이터 셋에서 EM 65.84%, F1 78.98%의 성능을 보였다.

  • PDF

Multi-level Attention Fusion Network for Machine Reading Comprehension (Multi-level Attention Fusion을 이용한 기계독해)

  • Park, Kwang-Hyeon;Na, Seung-Hoon;Choi, Yun-Su;Chang, Du-Seong
    • Annual Conference on Human and Language Technology
    • /
    • /
    • pp.259-262
    • /
    • 2018
  • 기계독해의 목표는 기계가 주어진 문맥을 이해하고 문맥에 대한 질문에 대답할 수 있도록 하는 것이다. 본 논문에서는 Multi-level Attention에 정보를 효율적으로 융합 수 있는 Fusion 함수를 결합하고, Answer module에Stochastic multi-step answer를 적용하여 SQuAD dev 데이터 셋에서 EM=78.63%, F1=86.36%의 성능을 보였다.

  • PDF

The Unsupervised Learning-based Language Modeling of Word Comprehension in Korean

  • Kim, Euhee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.24 no.11
    • /
    • pp.41-49
    • /
    • 2019
  • We are to build an unsupervised machine learning-based language model which can estimate the amount of information that are in need to process words consisting of subword-level morphemes and syllables. We are then to investigate whether the reading times of words reflecting their morphemic and syllabic structures are predicted by an information-theoretic measure such as surprisal. Specifically, the proposed Morfessor-based unsupervised machine learning model is first to be trained on the large dataset of sentences on Sejong Corpus and is then to be applied to estimate the information-theoretic measure on each word in the test data of Korean words. The reading times of the words in the test data are to be recruited from Korean Lexicon Project (KLP) Database. A comparison between the information-theoretic measures of the words in point and the corresponding reading times by using a linear mixed effect model reveals a reliable correlation between surprisal and reading time. We conclude that surprisal is positively related to the processing effort (i.e. reading time), confirming the surprisal hypothesis.

The Effect of College-Language Small Group Cooperative Learning on English Reading Comprehension, English Reading Motivation and Cooperative Learning Awareness (대학 교양영어 소집단 협동학습이 영어독해력, 영어읽기동기, 협동학습인식에 미치는 영향)

  • Lee, Young-Eun
    • Journal of Digital Convergence
    • /
    • v.18 no.6
    • /
    • pp.81-91
    • /
    • 2020
  • The purpose of this study is to analyze the effect of group co-learning on English reading ability and motivation and the change in group co-learning perception after planning and applying a group co-study class program that can be applied in university liberal arts English class. In order to achieve this goal, the experiment team (34 students) conducted the class from September 2 to December 13, 2019 for 62 freshmen who participated in the compulsory liberal arts English class at the four-year university in North Chungcheong Province, and the control team (28 students) conducted the class as a typical lecture class based on the basis of cooperative learning. The English proficiency of the learners was approached by dividing the area of academic proficiency into English reading skills and the area of justice into English reading motivations. The pre-experimental learners' English reading skills were measured by excerpting the national level educational achievement assessment (high 2). The research results are as follows. First, it was shown that the English reading ability score of a group that applied group cooperative learning and the English reading ability score of a group that did not apply group cooperative learning were statistically significant differences. Second, there was a difference between the English reading motivation score of the group applying the convocation group cooperative learning and the English reading motivation score of the group not applied. Third, the change in the perception of groups applying the convocation group cooperative learning occurred before and after the experiment. This study found that the awareness of English reading, English reading motivation, and cooperative learning increased through cooperative learning among university students during liberal arts English classes, which has a positive effect on self-identity and so on.