More Like this

1. Complex Factoid Question Answering with a Free-Text Knowledge Graph

   https://doi.org/10.1145/3366423.3380197  

   Zhao, Chen; Xiong, Chenyan; Qian, Xin; Boyd-Graber, Jordan (April 2020, WWW '20: Proceedings of The Web Conference 2020)

   null (Ed.)

   We introduce delft, a factoid question answering system which combines the nuance and depth of knowledge graph question answering approaches with the broader coverage of free-text. delft builds a free-text knowledge graph from Wikipedia, with entities as nodes and sentences in which entities co-occur as edges. For each question, delft finds the subgraph linking question entity nodes to candidates using text sentences as edges, creating a dense and high coverage semantic graph. A novel graph neural network reasons over the free-text graph—combining evidence on the nodes via information along edge sentences—to select a final answer. Experiments on three question answering datasets show delft can answer entity-rich questions better than machine reading based models, bert-based answer ranking and memory networks. delft’s advantage comes from both the high coverage of its free-text knowledge graph—more than double that of dbpedia relations—and the novel graph neural network which reasons on the rich but noisy free-text evidence. 

   more » « less
2. An XR GUI for Visualizing Messages in ECS Architectures

   https://doi.org/10.1109/ISMAR-Adjunct64951.2024.00189  

   Yang, Ben; He, Xichen; Li, Jace; Elvezio, Carmine; Feiner, Steven K (October 2024, IEEE International Symposium on Mixed and Augmented Reality Adjunct 2024)

   Entity–Component–System (ECS) architectures are fundamental to many systems for developing extended reality (XR) applications. These applications often contain complex scenes and require intricately connected application logic to connect components together, making debugging and analysis difficult. Graph-based tools have been created to show actions in ECS-based scene hierarchies, but few address interactions that go beyond traditional hierarchical communication. To address this, we present an XR GUI for Mercury (a toolkit to handle cross-component ECS communication) that allows developers to view and edit relationships and interactions between scene entities in Mercury. 

   more » « less
3. Attentive Relational Networks for Mapping Images to Scene Graphs

   Qi, Mengshi; Li, Weijian Li; Yang, Zhengyuan; Wang, Yunhong; Luo, Jiebo (January 2019, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition)

   Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships. Despite the recent success in object detection using deep learning techniques, inferring complex contextual relationships and structured graph representations from visual data remains a challenging topic. In this study, we propose a novel Attentive Relational Network that consists of two key modules with an object detection backbone to approach this problem. The first module is a semantic transformation module utilized to capture semantic embedded relation features, by translating visual features and linguistic features into a common semantic space. The other module is a graph self-attention module introduced to embed a joint graph representation through assigning various importance weights to neighboring nodes. Finally, accurate scene graphs are produced by the relation inference module to recognize all entities and the corresponding relations. We evaluate our proposed method on the widely-adopted Visual Genome dataset, and the results demonstrate the effectiveness and superiority of our model. 

   more » « less
4. Clustering-based Inference for Zero-Shot Biomedical Entity Linking

   Angell, Rico; Monath, Nicholas; Mohan, Sunil; Yadav, Nishant; McCallum, Andrew (January 2021, Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies)

   null (Ed.)

   Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned representations of entities. Previous approaches link each mention independently, ignoring the relationships within and across documents between the entity mentions. These relations can be very useful for linking mentions in biomedical text where linking decisions are often difficult due mentions having a generic or a highly specialized form. In this paper, we introduce a model in which linking decisions can be made not merely by linking to a knowledge base entity but also by grouping multiple mentions together via clustering and jointly making linking predictions. In experiments on the largest publicly available biomedical dataset, we improve the best independent prediction for entity linking by 3.0 points of accuracy, and our clustering-based inference model further improves entity linking by 2.3 points. 

   more » « less
5. One-Class Order Embedding for Dependency Relation Prediction

   https://doi.org/10.1145/3331184.3331249  

   Chiang, Meng-Fen; Lim, Ee-Peng; Lee, Wang-Chien; Ashok, Xavier Jayaraj; Prasetyo, Philips Kokoh (July 2019, Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval)

   Learning the dependency relations among entities and the hierarchy formed by these relations by mapping entities into some order embedding space can effectively enable several important applications, including knowledge base completion and prerequisite relations prediction. Nevertheless, it is very challenging to learn a good order embedding due to the existence of partial ordering and missing relations in the observed data. Moreover, most application scenarios do not provide non-trivial negative dependency relation instances. We therefore propose a framework that performs dependency relation prediction by exploring both rich semantic and hierarchical structure information in the data. In particular, we propose several negative sampling strategies based on graph-specific centrality properties, which supplement the positive dependency relations with appropriate negative samples to effectively learn order embeddings. This research not only addresses the needs of automatically recovering missing dependency relations, but also unravels dependencies among entities using several real-world datasets, such as course dependency hierarchy involving course prerequisite relations, job hierarchy in organizations, and paper citation hierarchy. Extensive experiments are conducted on both synthetic and real-world datasets to demonstrate the prediction accuracy as well as to gain insights using the learned order embedding. 

   more » « less