Filters








766 Hits in 2.0 sec

Rule Induction and Reasoning over Knowledge Graphs [chapter]

Daria Stepanova, Mohamed H. Gad-Elrab, Vinh Thinh Ho
2018 Lecture Notes in Computer Science  
Advances in information extraction have enabled the automatic construction of large knowledge graphs (KGs) like DBpedia, Freebase, YAGO and Wikidata. Learning rules from KGs is a crucial task for KG completion, cleaning and curation. This tutorial presents state-ofthe-art rule induction methods, recent advances, research opportunities as well as open challenges along this avenue. We put a particular emphasis on the problems of learning exception-enriched rules from highly biased and incomplete
more » ... ata. Finally, we discuss possible extensions of classical rule induction techniques to account for unstructured resources (e.g., text) along with the structured ones.
doi:10.1007/978-3-030-00338-8_6 fatcat:xvbbxrcdd5efvhqy5is5gfpbge

Learning Rules from Incomplete KGs using Embeddings

Vinh Thinh Ho, Daria Stepanova, Mohamed H. Gad-Elrab, Evgeny Kharlamov, Gerhard Weikum
2018 International Semantic Web Conference  
Rules over a Knowledge Graph (KG) capture interpretable patterns in data and various methods for rule learning have been proposed. Since KGs are inherently incomplete, rules can be used to deduce missing facts. Statistical measures for learned rules such as confidence reflect rule quality well when the KG is reasonably complete; however, these measures might be misleading otherwise. So it is difficult to learn high-quality rules from the KG alone, and scalability dictates that only a small set
more » ... f candidate rules is generated. Therefore, the ranking and pruning of candidate rules is a major problem. To address this issue, we propose a rule learning method that utilizes probabilistic representations of missing facts. In particular, we iteratively extend rules induced from a KG by relying on feedback from a precomputed embedding model over the KG and external information sources including text corpora. Experiments on real-world KGs demonstrate the effectiveness of our novel approach both with respect to the quality of the learned rules and fact predictions that they produce.
dblp:conf/semweb/Ho0GKW18 fatcat:65ptz7siqrae3kvp6wtlw2acau

Extracting Contextualized Quantity Facts from Web Tables

Vinh Thinh Ho, Koninika Pal, Simon Razniewski, Klaus Berberich, Gerhard Weikum
2021 Proceedings of the Web Conference 2021  
Quantity queries, with filter conditions on quantitative measures of entities, are beyond the functionality of search engines and QA assistants. To enable such queries over web contents, this paper develops a novel method for automatically extracting quantity facts from ad-hoc web tables. This involves recognizing quantities, with normalized values and units, aligning them with the proper entities, and contextualizing these pairs with informative cues to match sophisticated queries with
more » ... s. Our method includes a new approach to aligning quantity columns to entity columns. Prior works assumed a single subject-column per table, whereas our approach is geared for complex tables and leverages external corpora as evidence. For contextualization, we identify informative cues from text and structural markup that surrounds a table. For querytime fact ranking, we devise a new scoring technique that exploits both context similarity and inter-fact consistency. Comparisons of our building blocks against state-of-the-art baselines and extrinsic experiments with two query benchmarks demonstrate the benefits of our method.
doi:10.1145/3442381.3450072 fatcat:p7l4as6amre33kqdlkua7kwj64

Enhancing Knowledge Bases with Quantity Facts

Vinh Thinh Ho, Daria Stepanova, Dragan Milchevski, Jannik Strötgen, Gerhard Weikum
2022 Proceedings of the ACM Web Conference 2022  
Machine knowledge about the world's entities should include quantity properties, such as heights of buildings, running times of athletes, energy efficiency of car models, energy production of power plants, and more. State-of-the-art knowledge bases (KBs), such as Wikidata, cover many relevant entities but often miss the corresponding quantities. Prior work on extracting quantity facts from web contents focused on high precision for top-ranked outputs, but did not tackle the KB coverage issue.
more » ... is paper presents a recalloriented approach which aims to close this gap in knowledge-base coverage. Our method is based on iterative learning for extracting quantity facts, with two novel contributions to boost recall for KB augmentation without sacrificing the quality standards of the knowledge base. The first contribution is a query expansion technique to capture a larger pool of fact candidates. The second contribution is a novel technique for harnessing observations on value distributions for self-consistency. Experiments with extractions from more than 13 million web documents demonstrate the benefits of our method.
doi:10.1145/3485447.3511932 fatcat:hkyzkbg32zb6po7467kbfw5a7y

Rule Learning from Knowledge Graphs Guided by Embedding Models [chapter]

Vinh Thinh Ho, Daria Stepanova, Mohamed H. Gad-Elrab, Evgeny Kharlamov, Gerhard Weikum
2018 Lecture Notes in Computer Science  
Rules over a Knowledge Graph (KG) capture interpretable patterns in data and various methods for rule learning have been proposed. Since KGs are inherently incomplete, rules can be used to deduce missing facts. Statistical measures for learned rules such as confidence reflect rule quality well when the KG is reasonably complete; however, these measures might be misleading otherwise. So it is difficult to learn high-quality rules from the KG alone, and scalability dictates that only a small set
more » ... f candidate rules is generated. Therefore, the ranking and pruning of candidate rules is a major problem. To address this issue, we propose a rule learning method that utilizes probabilistic representations of missing facts. In particular, we iteratively extend rules induced from a KG by relying on feedback from a precomputed embedding model over the KG and external information sources including text corpora. Experiments on real-world KGs demonstrate the effectiveness of our novel approach both with respect to the quality of the learned rules and fact predictions that they produce.
doi:10.1007/978-3-030-00671-6_5 fatcat:bikowhokvbes5na3ij7dtdrjyy

QuTE: Answering Quantity Queries from Web Tables

Vinh Thinh Ho, Koninika Pal, Gerhard Weikum
2021 Proceedings of the 2021 International Conference on Management of Data  
Quantities are financial, technological, physical and other measures that denote relevant properties of entities, such as revenue of companies, energy efficiency of cars or distance and brightness of stars and galaxies. Queries with filter conditions on quantities are an important building block for downstream analytics, and pose challenges when the content of interest is spread across a huge number of web tables and other ad-hoc datasets. Search engines support quantity lookups, but largely
more » ... l on quantity filters. The QuTE system presented in this paper aims to overcome these problems. It comprises methods for automatically extracting entity-quantity facts from web tables, as well as methods for online query processing, with new techniques for query matching and answer ranking.
doi:10.1145/3448016.3452763 fatcat:yezokhuhkffbthapyhlwy7yzom

Towards Utilizing Knowledge Graph Embedding Models for Conceptual Clustering

Mohamed H. Gad-Elrab, Vinh Thinh Ho, Evgeny Levinkov, Trung-Kien Tran, Daria Stepanova
2020 International Semantic Web Conference  
We propose a framework to utilize Knowledge Graph (KG) embedding models for conceptual clustering, i.e., the task of clustering a given set of entities in a KG based on the quality of the resulting descriptions for the clusters. Specifically, prominent regions in the embedding space are detected using Multicut clustering algorithm, and then the queries describing/covering the entities within these regions are obtained by rule learning. Finally, we evaluate these queries using different metrics.
more » ... In our preliminary experiments, we compare the suitability of well-known KG embedding models for conceptual clustering. The reported results provide insights for the capability of these embeddings to capture graph topology and their applicability for data mining tasks beyond link prediction. Recent advances in (deep) representation learning on KGs have proved to be effective for specialized tasks such as KG completion [16] and conjunctive query (CQ) answering [8, 13, 6] . In particular, in [13] queries are embedded as boxes/hyper-rectangles in the embedding space, where interior points of these boxes correspond to the set of query's answers.
dblp:conf/semweb/Gad-ElrabHLTS20 fatcat:3idrwcvctrgrvmf5f3xmwaxrvm

ANTHROPOMETRIC IDENTIFICATION SYSTEM USING CONVOLUTION NEURAL NETWORK BASED ON REGION PROPOSAL NETWORK

Ho Nguyen Anh Tuan, Pham Dang Dieu, Nguyen Dao Xuan Hai, Nguyen Truong Thinh, Le Gia Vinh
2021 Y học Việt Nam  
The operating of the anthropometric identification supported byConvolution Neural Network system is to locate precious anthropology spots and certaindistances between each feature area on a person's face. Identifies the anthropometricpoints from 2D captured pictures by 3 perspective views promised an implementation between medical diagnostics to solve the problem of data retrieval time and efficiency compared to other manual measures.
doi:10.51298/vmj.v506i1-2.989 fatcat:qt7qzhdwf5hjnllvc35ydcuizq

Hiệu quả của kỹ thuật tưới tiết kiệm nước trên cây trồng cạn ở vùng đất Giồng Cát tỉnh Trà Vinh

Hồng Minh Hoàng, Nguyễn Hồng Tín, Thạch Dương Nhân, Lê Văn Mưa, Hồ Chí Thịnh, Võ Thùy Dương, Tô Thị Lai Hón
2018 Can Tho University Journal of Science  
The study was aimed to compare efficiency between water-saving irrigation techniques (WSI) and traditional irrigation practices applied on upland crops in sandy soil areas in Tra Vinh province to provide  ...  , and build a pilot trial for evaluating the effectiveness of the WSI model that was applied on watermelon and groundnut crops (representatives of upland crops) in Cau Ngang and Tra Cu districts, Tra Vinh  ...  Trích dẫn: Hồng Minh Hoàng, Nguyễn Hồng Tín, Hồ Chí Thịnh, Võ Thùy Dương, Tô Thị Lai Hón, Thạch Dương Nhân và Lê Văn Mưa, 2018.  ... 
doi:10.22144/ctu.jvn.2018.140 fatcat:rmslkis4mzglberpwe4r3wfybi

Nồng độ quinalphos trong nước, cá chép (Cyprinus carpio) và cá mè vinh (Barbonymus gonionotus) trong mô hình lúa cá kết hợp

Nguyễn Quốc Thịnh, Nguyễn Thanh Phương, Đỗ Thị Thanh Hương, Trần Minh Phú, Patrick Kestemont, Hồ Thị Bích Tuyền, Caroline Douny, Marie-Louise Scippo, Nguyễn Văn Quí
2016 Can Tho University Journal of Science  
Trích dẫn: Nguyễn Quốc Thịnh, Trần Minh Phú, Caroline Douny, Nguyễn Thanh Phương, Đỗ Thị Thanh Hương, Patrick Kestemont, Nguyễn Văn Quí, Hồ Thị Bích Tuyền và Marie-Louise Scippo, 2016.  ...  và nhóm PCP khác nhau theo loài cá mặc dù các mẫu được thu cùng một địa điểm, cụ thể đối với dieldrin, nồng độ nhiễm đối với cá chình là 15,82 µg/kg trong khi đó nồng độ này đối với một loài cá thuộc họ  ... 
doi:10.22144/ctu.jvn.2016.464 fatcat:i2s6akyifzdafgasdex6wdmn54

Author Index

2020 2020 International Conference on Advanced Computing and Applications (ACOMP)  
Tran 15 Truong, Quang Vinh 150 Van, Toan Pham 23, 49 Vinh, Truong Quang 146 Vo, Dinh-Hieu 79 Vu, Thang Nguyen 29 Yoshimi, Masato 71  ...  71 Ngo, Ha Quang Thinh 101, 150 Ngon, Nguyen Chi 165 Nguyen, Anh Hai 130 Nguyen, Dang Tuan 94 Nguyen, Duy Manh Thi 130 Nguyen, Hieu-Cuong 135 Nguyen, Hoai Viet 49 Nguyen, Hue  ... 
doi:10.1109/acomp50827.2020.00035 fatcat:ck4mtzmkuvcvpjol72bxksxipm

A preliminary list of the subfamily Cerambycinae (Coleoptera: Cerambycidae) of Vietnam

Cao Thi Nga, Khuat Dang Long
2014 TAP CHI SINH HOC  
Hoang Vu Tru, Ta Huy Thinh, Cao Quynh Nga, 2011. Result of the survey on longhorn beetles (Cerambycidae, Coleoptera) along the Ho Chi Minh road through Tay Nguyen highland.  ...  The subfamily classification of this study TÓM TẮT Cerambycinae là một trong các phân họ lớn thuộc họ Xén tóc Cerambicidae, sâu non của chúng sống trong thân cây ñang còn sống hoặc cây ñã chết khô,  ... 
doi:10.15625/0866-7160/v36i1.4514 fatcat:lxr3g5tqjvcitklqq3uxt6mlfe

Ultra-Deep Sequencing of Plasma-Circulating DNA for the Detection of Tumor- Derived Mutations in Patients with Nonmetastatic Colorectal Cancer

Huu-Thinh Nguyen, Bac An Luong, Duc-Huy Tran, Trong-Hieu Nguyen, Quoc Dat Ngo, Linh Gia Hoang Le, Quoc Chuong Ho, Hue-Hanh Thi Nguyen, Cao Minh Nguyen, Vu Uyen Tran, Truong Vinh Ngoc Pham, Minh Triet Le (+15 others)
2022 figshare.com  
Identification of tumor-derived mutation (TDM) in liquid biopsies (LB), especially in early-stage patients, faces several challenges, including low variant-allele frequencies, interference by white blood cell (WBC)-derived mutations (WDM), benign somatic mutations and tumor heterogeneity. Here, we addressed the above-mentioned challenges in a cohort of 50 nonmetastatic colorectal cancer patients, via a workflow involving parallel sequencing of paired WBC- and tumor-gDNA. After excluding
more » ... l false positive mutations, we detected at least one TDM in LB of 56% (28/50) of patients, with the majority showing low-patient coverage, except for one TDM mapped to KMT2D that recurred in 30% (15/30) of patients.
doi:10.6084/m9.figshare.17371905.v2 fatcat:kqr32lpgi5gyplqfolyl3gqowu

Phylodynamics of Enterovirus A71-Associated Hand, Foot, and Mouth Disease in Viet Nam

Jemma L. Geoghegan, Le Van Tan, Denise Kühnert, Rebecca A. Halpin, Xudong Lin, Ari Simenauer, Asmik Akopov, Suman R. Das, Timothy B. Stockwell, Susmita Shrivastava, Nghiem My Ngoc, Le Thi Tam Uyen (+21 others)
2015 Journal of Virology  
All of the hospitals are located in Ho Chi Minh City (HCMC) and serve a population of 42 million people.  ... 
doi:10.1128/jvi.00706-15 pmid:26085170 pmcid:PMC4524079 fatcat:ihabc5aotjexrn6fblbt43ig3q

Authors Index

2021 2021 International Conference on System Science and Engineering (ICSSE)  
Hsieh, 452 Hai Dang Le, 151 Hai Xuan Le, 412 Ha-Nam Nguyen, 111 Ha-Phuong Vu, 237 Herleeyandi Markoni, 442 Ho Duc Tuan, 23, 393 Ho Pham Huy Anh, 62, 69 Ho Sy Phuong, 279 Hoa Bui Thanh  ...  , 200 Van-Tri Bui, 176 Van-Truong Phan, 138 Van-Vinh Le, 360 Vi H.  ... 
doi:10.1109/icsse52999.2021.9538413 fatcat:et3qkvsrwzdz5jb72osp3alroi
« Previous Showing results 1 — 15 out of 766 results