Naver Corporation

About: Naver Corporation is a company organization based out in Seongnam-si, South Korea. It is known for research contribution in the topics: Terminal (electronics) & Computer science. The organization has 4038 authors who have published 4294 publications receiving 35045 citations. The organization is also known as: NAVER Corporation & NAVER.

System and method for transforming vernacular pronunciation

Abstract: Provided is a system and method for transforming vernacular pronunciation with respect to Hanja using a statistical method. In a system for transforming vernacular pronunciation, a vernacular pronunciation extracting unit extracts a vernacular pronunciation with respect to a Hanja character string, a statistical data determining unit determines a statistical data with respect to the Hanja character string by using statistical data of features related to a Hanja-vernacular pronunciation transformation, and a vernacular pronunciation transforming unit transforms the Hanja character string into a vernacular pronunciation using the extracted vernacular pronunciation and the determined statistical data.

Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information

Abstract: Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship between two sentences is required but it is yet challenging. Although attention mechanism is useful to capture the semantic relationship and to properly align the elements of two sentences, previous methods of attention mechanism simply use a summation operation which does not retain original features enough. Inspired by DenseNet, a densely connected convolutional network, we propose a densely-connected co-attentive recurrent neural network, each layer of which uses concatenated information of attentive features as well as hidden features of all the preceding recurrent layers. It enables preserving the original and the co-attentive feature information from the bottommost word embedding layer to the uppermost recurrent layer. To alleviate the problem of an ever-increasing size of feature vectors due to dense concatenation operations, we also propose to use an autoencoder after dense concatenation. We evaluate our proposed architecture on highly competitive benchmark datasets related to sentence matching. Experimental results show that our architecture, which retains recurrent and attentive features, achieves state-of-the-art performances for most of the tasks.

Learning De-biased Representations with Biased Representations

Abstract: Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able to tell if models are relying on dataset biases as shortcuts for successful prediction (e.g., using snow cues for recognising snowmobiles), resulting in biased models that fail to generalise when the bias shifts to a different class. The cross-bias generalisation problem has been addressed by de-biasing training data through augmentation or re-sampling, which are often prohibitive due to the data collection cost (e.g., collecting images of a snowmobile on a desert) and the difficulty of quantifying or expressing biases in the first place. In this work, we propose a novel framework to train a de-biased representation by encouraging it to be different from a set of representations that are biased by design. This tactic is feasible in many scenarios where it is much easier to define a set of biased representations than to define and quantify bias. We demonstrate the efficacy of our method across a variety of synthetic and real-world biases; our experiments show that the method discourages models from taking bias shortcuts, resulting in improved generalisation. Source code is available at this https URL.

The Beneficial Effect of Vanillic Acid on Ulcerative Colitis

Abstract: Vanillic acid, an oxidized form of vanillin, is a benzoic acid derivative used as a flavoring agent. The objective of this study was to determine whether vanillic acid has beneficial effects against dextran sulfate sodium (DSS)-induced ulcerative colitis. Our results showed that vanillic acid reduced the severity of the clinical signs of DSS-induced colitis, including weight loss and shortening of colon length, and the disease activity index. The results of this study showed that vanillic acid significantly suppressed the expression of cyclooxygenase-2 and the activation of transcription nuclear factor-kB p65 in DSS-treated colon tissues. In addition, we observed that the plasma levels of interleukin (IL)-6 were higher in the DSS-treated group than in the control group, but these increased levels were reduced by the administration of vanillic acid. Taken together, these findings suggest that vanillic acid has a beneficial effect on DSS-induced ulcerative colitis, thereby indicating its usefulness in the regulation of chronic intestinal inflammation.

Method and system for controlling browser by using image

Abstract: Browser controlling method and system using an image are provided. The method includes inputting an image; recognizing the image; and executing a command based on the recognized image. Accordingly, the command based on the user's input image can be executed in the browser. Also, since the browser does not need to display various function buttons, the screen can be utilized more efficiently.