عنوان

Mining structures of factual knowledge from text :

شابک

1681733935

شابک

9781681733937

شابک اشتباه

1681733927

شابک اشتباه

1681733943

شابک اشتباه

9781681733920

شابک اشتباه

9781681733944

عنوان اصلي

Mining structures of factual knowledge from text :

نام عام مواد

[Book]

ساير اطلاعات عنواني

an effort-light approach /

نام نخستين پديدآور

Xiang Ren, University of Southern California ; Jiawei Han, University of Illinois at Urbana-Champaign.

محل نشرو پخش و غیره

[San Rafael, California] :

نام ناشر، پخش کننده و غيره

Morgan & Claypool Publishers,

تاریخ نشرو بخش و غیره

[2018]

تاریخ نشرو بخش و غیره

©2018

نام خاص و کميت اثر

1 online resource (xv, 183 pages) :

ساير جزييات

illustrations

عنوان فروست

Synthesis lectures on data mining and knowledge discovery,

مشخصه جلد

#15

شاپا ي ISSN فروست

2151-0075 ;

متن يادداشت

Includes bibliographical references (pages 167-181).

متن يادداشت

Introduction -- Background -- Literature review -- Entity recognition and typing with knowledge bases -- Fine-grained entity typing with knowledge bases -- Synonym discovery from large corpus / Meng Qu -- Joint extraction of typed entities and relationships -- Pattern-enhanced embedding learning for relation extraction / Meng Qu -- Heterogeneous supervision for relation extraction / Liyuan Liu -- Indirect supervision: leveraging knowledge from auxiliary tasks / Zeqiu Wu -- Mining entity attribute values with meta patterns / Meng Jiang -- Open information extraction with global structure cohesiveness / Qi Zhu -- Applications -- Conclusion -- Vision and future work.

بدون عنوان

0

متن يادداشت

The real-world data, though massive, is largely unstructured, in the form of natural-language text. It is challenging but highly desirable to mine structures from massive text data, without extensive human annotation and labeling. In this book, we investigate the principles and methodologies of mining structures of factual knowledge (e.g., entities and their relationships) from massive, unstructured text corpora. Departing from many existing structure extraction methods that have heavy reliance on human annotated data for model training, our effort-light approach leverages human-curated facts stored in external knowledge bases as distant supervision and exploits rich data redundancy in large text corpora for context understanding. This effort-light mining approach leads to a series of new principles and powerful methodologies for structuring text corpora, including: (1) entity recognition, typing, and synonym discovery; (2) entity relation extraction; and (3) open-domain attribute-value mining and information extraction. This book introduces this new research frontier and points out some promising research directions.

عنوان

MINING STRUCTURES OF FACTUAL KNOWLEDGE FROM TEXT.

شماره استاندارد بين المللي کتاب و موسيقي

1681733943

موضوع مستند نشده

Data mining.

موضوع مستند نشده

Data structures (Computer science)

موضوع مستند نشده

Electronic information resource searching.

موضوع مستند نشده

Natural language processing (Computer science)

موضوع مستند نشده

COMPUTERS-- General.

موضوع مستند نشده

Data mining.

موضوع مستند نشده

Data structures (Computer science)

موضوع مستند نشده

Electronic information resource searching.

موضوع مستند نشده

Natural language processing (Computer science)

موضوع مستند نشده

COM-- 000000

شماره

ويراست

شماره رده

نشانه اثر

مستند نام اشخاص تاييد نشده

Ren, Xiang, (Computer scientist)

مستند نام اشخاص تاييد نشده

Han, Jiawei

تاريخ عمليات

20200823052142.0

قواعد فهرست نويسي ( بخش توصيفي )

pn

نام الکترونيکي

نوع ماده

[Book]

تكميل شده

Y