大葉大學圖書館 |

Adding Semantics to Unstructured and Semi-structured Data on the Web.

紀錄類型:	書目-電子資源 : Monograph/item
書名/作者:	Adding Semantics to Unstructured and Semi-structured Data on the Web.
作者:	Bhagavatula, Chandra Sekhar.
出版者:	Ann Arbor : : ProQuest Dissertations & Theses, , 2016
面頁冊數:	88 p.
附註:	Source: Dissertation Abstracts International, Volume: 77-10(E), Section: B.
Contained By:	Dissertation Abstracts International77-10B(E).
標題:	Computer science.
ISBN:	9781339785486
摘要、提要註:	Acquiring vast bodies of knowledge in machine-understandable form is one of the main challenges in artificial intelligence. Information Extraction is the task of automatically extracting structured, machine-understandable information from unstructured or semi-structured data. Recent advances in information extraction and the massive scale of data on the Web present a unique opportunity for artificial intelligence systems for large-scale automatic knowledge acquisition. However, to realize the full potential of the automatically extracted information, it is essential to understand their semantics.

Adding Semantics to Unstructured and Semi-structured Data on the Web.
Bhagavatula, Chandra Sekhar.

Adding Semantics to Unstructured and Semi-structured Data on the Web. - Ann Arbor : ProQuest Dissertations & Theses, 2016 - 88 p.

Source: Dissertation Abstracts International, Volume: 77-10(E), Section: B.

Thesis (Ph.D.)--Northwestern University, 2016.

Acquiring vast bodies of knowledge in machine-understandable form is one of the main challenges in artificial intelligence. Information Extraction is the task of automatically extracting structured, machine-understandable information from unstructured or semi-structured data. Recent advances in information extraction and the massive scale of data on the Web present a unique opportunity for artificial intelligence systems for large-scale automatic knowledge acquisition. However, to realize the full potential of the automatically extracted information, it is essential to understand their semantics.

ISBN: 9781339785486Subjects--Topical Terms:

182962
Computer science.

Adding Semantics to Unstructured and Semi-structured Data on the Web.
LDR:02912nmm a2200289 4500 001 476193
005 20170614101403.5
008 181208s2016 ||||||||||||||||| ||eng d
020 $a 9781339785486
035 $a (MiAaPQ)AAI10117145
035 $a AAI10117145
040 $a MiAaPQ $c MiAaPQ
100 1 $a Bhagavatula, Chandra Sekhar. $0 (orcid)0000-0003-3714-5740 $3 686737
245 1 0 $a Adding Semantics to Unstructured and Semi-structured Data on the Web.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2016
300 $a 88 p.
500 $a Source: Dissertation Abstracts International, Volume: 77-10(E), Section: B.
500 $a Adviser: Doug Downey.
502 $a Thesis (Ph.D.)--Northwestern University, 2016.
520 $a Acquiring vast bodies of knowledge in machine-understandable form is one of the main challenges in artificial intelligence. Information Extraction is the task of automatically extracting structured, machine-understandable information from unstructured or semi-structured data. Recent advances in information extraction and the massive scale of data on the Web present a unique opportunity for artificial intelligence systems for large-scale automatic knowledge acquisition. However, to realize the full potential of the automatically extracted information, it is essential to understand their semantics.
520 $a A key step in understanding the semantics of extracted information is entity linking: the task of mapping a phrase in text to its referent entity in a given knowledge base. In addition to identifying entities mentioned in text, an AI system can benefit significantly from the organization of entities in a taxonomy. While taxonomies are used in a variety of applications, including IBM's Jeopardy-winning Watson system, they demand significant effort in their creation. They are either manually curated, or built using semi-supervised machine learning techniques.
520 $a This dissertation explores methods to automatically infer a taxonomy of entities, given the properties that are usually associated with them (e.g. as a City, Chicago is usually associated with properties like "population" and "area"). Our approach is based on the Property Inheritance hypothesis, which states that entities of a specific type in a taxonomy inherit properties from more general types. We apply this hypothesis to two distinct information extraction tasks --- each of which is aimed at understanding the semantics of information mined from the Web. First, we describe the two systems (1) TABEL: a state-of-the art system that performs the task of entity linking on Web tables, and (2) SKEY: a system that extracts key phrases that summarize a document in a given corpus. We then apply topic models that encode our hypothesis in a probabilistic framework to automatically infer a taxonomy in each task.
590 $a School code: 0163.
650 4 $a Computer science. $3 182962
690 $a 0984
710 2 0 $a Northwestern University. $b Computer Science. $3 686738
773 0 $t Dissertation Abstracts International $g 77-10B(E).
790 $a 0163
791 $a Ph.D.
792 $a 2016
793 $a English