Abstract-This paper presents a new selection-based question answering dataset, SelQA. The dataset consists of questions generated through crowdsourcing and sentence length answers that are drawn from the ten most prevalent topics in the English Wikipedia. We introduce a corpus annotation scheme that enhances the generation of large, diverse, and challenging datasets by explictly aiming to reduce word co-occurrences between the question and answers. Our annotation scheme is composed of a series of crowdsourcing tasks with a view to more effectively utilize crowdsourcing in the creation of question answering datasets in various domains. Several systems are compared on the tasks of answer sentence selection and answer triggering, providing strong baseline results for future work to improve upon.
This paper presents a new corpus and a robust deep learning architecture for a task in reading comprehension, passage completion, on multiparty dialog. Given a dialog in text and a passage containing factual descriptions about the dialog where mentions of the characters are replaced by blanks, the task is to fill the blanks with the most appropriate character names that reflect the contexts in the dialog. Since there is no dataset that challenges the task of passage completion in this genre, we create a corpus by selecting transcripts from a TV show that comprise 1,681 dialogs, generating passages for each dialog through crowdsourcing, and annotating mentions of characters in both the dialog and the passages. Given this dataset, we build a deep neural model that integrates rich feature extraction from convolutional neural networks into sequence modeling in recurrent neural networks, optimized by utterance and dialog level attentions. Our model outperforms the previous state-of-the-art model on this task in a different genre using bidirectional LSTM, showing a 13.0+% improvement for longer dialogs. Our analysis shows the effectiveness of the attention mechanisms and suggests a direction to machine comprehension on multiparty dialog.
Abstract. This paper presents a technique of incorporating anisotropic metric into the Delaunay triangulation algorithm for unstructured mesh generation on 3D parametric surfaces. Both empty circumcircle and inner angles criteria of Delaunay retriangulation can be successfully used with the developed method of coordinate transformation with little adjustments. We investigate the efficiency of mesh generation process for different criteria and the quality of obtained meshes.
The article presents a comparison of several octree-and kd-tree-based structures used for the construction of control space in the process of anisotropic mesh generation and adaptation. The adaptive control space utilized by the authors supervises the construction of meshes by providing the required metric information regarding the desired shape and size of elements of the mesh at each point of the modeled domain. Comparative tests of these auxiliary structures were carried out based on different versions of the tree structures with respect to computational and memory complexity as well as the quality of the generated mesh. Analysis of the results shows that kd-trees (not present in the meshing literature in this role) offer good performance and may become a reasonable alternative to octree structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.