Filters








27,198 Hits in 5.0 sec

Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries [article]

Yuke Zhu, Ce Zhang, Christopher Ré, Li Fei-Fei
2015 arXiv   pre-print
Building such a large-scale multimodal KB presents a major challenge of scalability.  ...  We cast a large-scale MRF into a KB representation, incorporating visual, textual and structured data, as well as their diverse relations.  ...  A KB can often be viewed as a large-scale graph structure that connects different entities with their relations [38, 58] .  ... 
arXiv:1507.05670v2 fatcat:fjcydziz6zbknegnvwa6xy6cyu

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  
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.  ...  Experiments with extractions from more than 13 million web documents demonstrate the benefits of our method.  ...  CONCLUSION We have presented a method for augmenting knowledge bases with quantity facts extracted from text at large scale.  ... 
doi:10.1145/3485447.3511932 fatcat:hkyzkbg32zb6po7467kbfw5a7y

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction [article]

Jason Weston, Antoine Bordes, Oksana Yakhnenko, Nicolas Usunier
2013 arXiv   pre-print
This paper proposes a novel approach for relation extraction from free text which is trained to jointly use information from the text and from existing knowledge.  ...  We empirically show on New York Times articles aligned with Freebase relations that our approach is able to efficiently use the extra information provided by a large subset of Freebase data (4M entities  ...  Experiments We use the training and test data, evaluation framework and baselines from (Riedel et al., 2010; Hoffmann et al., 2011; Surdeanu et al., 2012) .  ... 
arXiv:1307.7973v1 fatcat:rwctwdnpqnbapjlvmqufgpc5ka

Interactive Knowledge Base Population [article]

Travis Wolfe, Mark Dredze, James Mayfield, Paul McNamee, Craig Harman, Tim Finin, Benjamin Van Durme
2015 arXiv   pre-print
Most work on building knowledge bases has focused on collecting entities and facts from as large a collection of documents as possible.  ...  Lastly pocket KBs sidestep engineering issues around supporting a large global KB. The tools needed to do AI research on large KBs like Freebase range from cumbersome to lacking.  ...  result than building a global KB.  ... 
arXiv:1506.00301v1 fatcat:jtgxyijndbcvhfz7zr6jdz43j4

DeepDive: Web-scale Knowledge-base Construction using Statistical Learning and Inference

Feng Niu, Ce Zhang, Christopher Ré, Jude W. Shavlik
2012 International Workshop on Very Large Data Search  
We describe how we address the scalability challenges to achieve web-scale KBC and the lessons we have learned from building DeepDive.  ...  We present an end-to-end (live) demonstration system called DeepDive that performs knowledge-base construction (KBC) from hundreds of millions of web pages.  ...  INTRODUCTION Knowledge-base construction (KBC) is the process of populating a knowledge base (KB) with facts (or assertions) extracted from text.  ... 
dblp:conf/vlds/NiuZRS12 fatcat:okz2hruox5hg5e6vxhvmceoqoy

A Distributional Semantics Approach for Selective Reasoning on Commonsense Graph Knowledge Bases [chapter]

André Freitas, João Carlos Pereira da Silva, Edward Curry, Paul Buitelaar
2014 Lecture Notes in Computer Science  
Tasks such as question answering and semantic search are dependent on the ability of querying & reasoning over large-scale commonsense knowledge bases (KBs).  ...  This paper proposes a selective graph navigation mechanism based on a distributional relational semantic model which can be applied to querying & reasoning over heterogeneous knowledge bases (KBs).  ...  This research was supported in part by funding from the Science Foundation Ireland under Grant Number SFI/12/RC/2289 (Insight) and by the Irish Research Council. Joao C.  ... 
doi:10.1007/978-3-319-07983-7_3 fatcat:e4ebguwn5re7rijefhkza6pwqm

Knowledge bases in the age of big data analytics

Fabian M. Suchanek, Gerhard Weikum
2014 Proceedings of the VLDB Endowment  
This tutorial gives an overview on state-of-the-art methods for the automatic construction of large knowledge bases and harnessing them for data and text analytics.  ...  It covers both big-data methods for building knowledge bases and knowledge bases being assets for big-data applications. The tutorial also points out challenges and research opportunities.  ...  There is a large spectrum of methods to extract such facts from Web documents.  ... 
doi:10.14778/2733004.2733069 fatcat:kt3qjia2wbfctexlmyzs6cnqhq

Big Data Methods for Computational Linguistics

Gerhard Weikum, Johannes Hoffart, Ndapandula Nakashole, Marc Spaniol, Fabian M. Suchanek, Mohamed Amir Yosef
2012 IEEE Data Engineering Bulletin  
Specifically, we show how to build large dictionaries of names and paraphrases for entities and relations, and how these help to disambiguate entity mentions in texts.  ...  We demonstrate a virtuous cycle in harvesting knowledge from large data and text collections and leveraging this knowledge in order to improve the annotation and interpretation of language in Web pages  ...  Specifically, we show how to build large dictionaries of names and paraphrases for entities and relations, and how these help to disambiguate entity mentions in texts.  ... 
dblp:journals/debu/WeikumHNSSY12 fatcat:vmtel42ji5dfrebgn3ekt4lude

Entity ranking for descriptive queries

Kai Hong, Pengjun Pei, Ye-Yi Wang, Dilek Hakkani-Tur
2014 2014 IEEE Spoken Language Technology Workshop (SLT)  
First, we propose a novel method of injecting textual information from web documents to the KB on a large scale.  ...  Since the number of web documents can be large, we propose to use keyword extraction and summarization techniques for compactly representing entity-related information.  ...  We build different profiles for each entity in the KB, which we regard those profiles as unstructured text.  ... 
doi:10.1109/slt.2014.7078574 dblp:conf/slt/HongPWH14 fatcat:3mqqk7qr7rg6lht7r77iebt7y4

Dual-enhanced Word Representations Based on Knowledge Base

Fangyuan He, Yi Zhou, Haodi Zhang, Zhiyong Feng
2018 International Semantic Web Conference  
In this paper, we propose an approach for enhancing word representations twice based on large-scale knowledge bases.  ...  They commonly refer to the statistics derived from a large text corpus. Meanwhile, it is proved that the larger the corpus is, the better the model performs in most tasks [2, 4] .  ...  Firstly, we take the related words in knowledge base as the additional accurate context in comparison with the large corpus. Afterwards, inspired from Kiela et al.  ... 
dblp:conf/semweb/HeZZF18 fatcat:porhkmtogjefzdh3tjn2ey3sam

XLORE2: Large-scale Cross-lingual Knowledge Graph Construction and Application

Hailong Jin, Chengjiang Li, Jing Zhang, Lei Hou, Juanzi Li, Peng Zhang
2019 Data Intelligence  
But the number of aligned properties is quite small for such a large-scale KB.  ...  To address this issue, XLORE has become the first large-scale cross-lingual KB with a balanced amount of Chinese-English knowledge [4] .  ...  XLORE is the first large-scale cross-lingual KB with a balanced amount of Chinese-English knowledge.  ... 
doi:10.1162/dint_a_00003 dblp:journals/dint/JinLZHLZ19 fatcat:zdcq2gfyirc2ba4s6scxtytsna

Scalable Construction and Reasoning of Massive Knowledge Bases

Xiang Ren, Nanyun Peng, William Yang Wang
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts  
In today's information-based society, there is abundant knowledge out there carried in the form of natural language texts (e.g., news articles, social media posts, scientific publications), which spans  ...  How to turn such massive and unstructured text data into structured, actionable knowledge for computational machines, and furthermore, how to teach machines learn to reason and complete the extracted knowledge  ...  reasoning over large-scale knowledge bases.  ... 
doi:10.18653/v1/n18-6003 dblp:conf/naacl/RenPW18 fatcat:t57e7rwinjfbbgxzddcerishwi

Approximate and selective reasoning on knowledge graphs: A distributional semantics approach

André Freitas, João C.P. da Silva, Edward Curry, Paul Buitelaar
2015 Data & Knowledge Engineering  
Tasks such as question answering and semantic search are dependent on the ability of querying and reasoning over large-scale commonsense knowledge bases (KBs).  ...  This paper proposes a selective graph navigation mechanism based on a distributional relational semantic model which can be applied to querying and reasoning over heterogeneous knowledge bases (KBs).  ...  unstructured text is used as a general-purpose large-scale commonsense KB, which complements the knowledge present at the relational KB.  ... 
doi:10.1016/j.datak.2015.06.010 fatcat:6umcpjnmezfyzpvc53a7nbcvii

A Korean Knowledge Extraction System for Enriching a KBox

Sangha Nam, Eun-Kyung Kim, Jiho Kim, Yoosung Jung, Kijong Han, Key-Sun Choi
2018 International Conference on Computational Linguistics  
The increased demand for structured knowledge has created considerable interest in knowledge extraction from natural language sentences.  ...  Thus, it is widely used as an effective way to automatically create labeled data between a large-scale KB and a corpus.  ...  However, because even large-scale KBs do not contain all the possible knowledge, the knowledge completion task remains crucial in the NLP field.  ... 
dblp:conf/coling/NamKKJHC18 fatcat:3hxzfo2tojfw3lvewovupepm3i

Knowledge Graphs Representation for Event-Related E-News Articles

M.V.P.T. Lakshika, H.A. Caldera
2021 Machine Learning and Knowledge Extraction  
Thus, there is a striking concentration on constructing knowledge graphs by combining the background information related to the subjects in text documents.  ...  E-newspaper readers are overloaded with massive texts on e-news articles, and they usually mislead the reader who reads and understands information.  ...  Relationship Extraction Relation extraction is a key task of building large-scale KGs automatically by extracting unidentified relations from the source text.  ... 
doi:10.3390/make3040040 fatcat:hwspn2ma4vh5fn3o4oh3zgwj6m
« Previous Showing results 1 — 15 out of 27,198 results