• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• 한국정보컨버전스학회:학술대회논문집
• /
• 2008.06a
• /
• pp.53-56
• /
• 2008

This paper reports on the ACQA(Animated agent for Conversational Question Answering) project conducted at LIMSI. The aim is to design an expressive animated conversational agent(ACA) for conducting research along two main lines: 1/ perceptual experiments(eg perception of expressivity and 3D movements in both audio and visual channels): 2/ design of human-computer interfaces requiring head models at different resolutions and the integration of the talking head in virtual scenes. The target application of this expressive ACA is a real-time question and answer speech based system developed at LIMSI(RITEL). The architecture of the system is based on distributed modules exchanging messages through a network protocol. The main components of the system are: RITEL a question and answer system searching raw text, which is able to produce a text(the answer) and attitudinal information; this attitudinal information is then processed for delivering expressive tags; the text is converted into phoneme, viseme, and prosodic descriptions. Audio speech is generated by the LIMSI selection-concatenation text-to-speech engine. Visual speech is using MPEG4 keypoint-based animation, and is rendered in real-time by Virtual Choreographer (VirChor), a GPU-based 3D engine. Finally, visual and audio speech is played in a 3D audio and visual scene. The project also puts a lot of effort for realistic visual and audio 3D rendering. A new model of phoneme-dependant human radiation patterns is included in the speech synthesis system, so that the ACA can move in the virtual scene with realistic 3D visual and audio rendering.

• Journal of Digital Contents Society
• /
• v.11 no.3
• /
• pp.375-383
• /
• 2010

In developing question-answering (QA) systems, it is hard to analyze natural language questions syntactically and semantically and to find exact answers to given query questions. In order to avoid these difficulties, we propose a new style of question-answering system that automatically generate natural language queries and can allow to search queries fit for given keywords. The key idea behind generating natural queries is that after significant sentences within text documents are applied to the named entity recognition technique, we can generate a natural query (interrogative sentence) for each named entity (such as person, location, and time). The natural query is divided into two types: simple type and sentence structure type. With the large database of question-answer pairs, the system can easily obtain natural queries and their corresponding answers for given keywords. The most important issue is how to generate meaningful queries which can present unambiguous answers. To this end, we propose two principles to decide which declarative sentences can be the sources of natural queries and a pattern-based method for generating meaningful queries from the selected sentences.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.199-206
• /
• 2021

Rhetorical relations between two text fragments are essential information and support natural language processing applications such as Question - Answering (QA) system and automatic text summarization to produce an effective outcome. Question - Answering (QA) system facilitates users to retrieve a meaningful response. There is a demand for rhetorical relation based datasets to develop such a system to interpret and respond to user requests. There are a limited number of datasets for developing an Arabic QA system. Thus, there is a lack of an effective QA system in the Arabic language. Recent research works reveal that unsupervised learning can support the QA system to reply to users queries. In this study, researchers intend to develop a rhetorical relation based dataset for implementing unsupervised learning applications. A web crawler is developed to crawl Arabic content from the web. A discourse-annotated corpus is generated using the rhetorical structural theory. A Naïve Bayes based QA system is developed to evaluate the performance of datasets. The outcome shows that the performance of the QA system is improved with proposed dataset and able to answer user queries with an appropriate response. In addition, the results on fine-grained and coarse-grained relations reveal that the dataset is highly reliable.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• 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.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.339-346
• /
• 2017

There is increasing interest in text analysis based on unstructured data such as articles and comments, questions and answers. This is because they can be used to identify, evaluate, predict, and recommend features from unstructured text data, which is the opinion of people. The same holds true for TEL, where the MOOC service has evolved to automate debating, questioning and answering services based on the teaching-learning support system in order to generate question topics and to automatically classify the topics relevant to new questions based on question and answer data accumulated in the system. Therefore, in this study, we propose topic modeling using LDA to automatically classify new query topics. The proposed method enables the generation of a dictionary of question topics and the automatic classification of topics relevant to new questions. Experimentation showed high automatic classification of over 0.7 in some queries. The more new queries were included in the various topics, the better the automatic classification results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6080-6096
• /
• 2019

Text classification is one of the fundamental techniques in natural language processing. Numerous studies are based on text classification, such as news subject classification, question answering system classification, and movie review classification. Traditional text classification methods are used to extract features and then classify them. However, traditional methods are too complex to operate, and their accuracy is not sufficiently high. Recently, convolutional neural network (CNN) based one-hot method has been proposed in text classification to solve this problem. In this paper, we propose an improved method using CNN based skip-gram method for Chinese text classification and it conducts in Sogou news corpus. Experimental results indicate that CNN with the skip-gram model performs more efficiently than CNN-based one-hot method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.529-536
• /
• 2004

The main idea of this paper is to combine position information in sentence and query type classification to make the documents ranking to query more accessible. First, the use of conceptual graphs for the representation of document contents In information retrieval is discussed. The method is based on well-known strategies of text comparison, such as Dice Coefficient, with position-based weighted term. Second, we introduce a method for learning query type classification that improves the ability to retrieve answers to questions from Question Answering system. Proposed methods employ naive bayes classification in machine learning fields. And, we used a collection of approximately 30,000 question-answer pairs for training, obtained from Frequently Asked Question(FAQ) files on various subjects. The evaluation on a set of queries from international TREC-9 question answering track shows that the method with machine learning outperforms the underline other systems in TREC-9 (0.29 for mean reciprocal rank and 55.1% for precision).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.