知識表示(knowledge representation)是指把知識客體中的知識因子與知識關聯起來,便於人們識別和理解知識。知識表示是知識組織的前提和基礎,任何知識組織方法都是要建立在知識表示的基礎上。知識表示有主觀知識表示和客觀知識表示兩種。

VIP內容

簡介:計算機視覺研究大多都集中在不重疊的目標對象上,然而,目標對象卻不足以描述豐富的視覺知識,於是,研究者就通過語言特征來獲取更多的信息。通過圖片與文字敘述相結合的多模態信息融合來獲取一個場景圖譜。

場景要旨的吸引人的想法的困難在於,關於“要旨”的內容尚無共識。 場景中某些對象應至少是要點的一部分。必須將對象之間的某些關係編碼為要點。 即使將所有物體都相同,所要表達的含義卻不同。

圖表示學習無處不在:

對具有獨立對象和關係的特征進行學習,將獲得一個場景圖譜:

成為VIP會員查看完整內容
0
22
0

最新內容

One of the most important goals of digital humanities is to provide researchers with data and tools for new research questions, either by increasing the scale of scholarly studies, linking existing databases, or improving the accessibility of data. Here, the FAIR principles provide a useful framework as these state that data needs to be: Findable, as they are often scattered among various sources; Accessible, since some might be offline or behind paywalls; Interoperable, thus using standard knowledge representation formats and shared vocabularies; and Reusable, through adequate licensing and permissions. Integrating data from diverse humanities domains is not trivial, research questions such as "was economic wealth equally distributed in the 18th century?", or "what are narratives constructed around disruptive media events?") and preparation phases (e.g. data collection, knowledge organisation, cleaning) of scholars need to be taken into account. In this chapter, we describe the ontologies and tools developed and integrated in the Dutch national project CLARIAH to address these issues across datasets from three fundamental domains or "pillars" of the humanities (linguistics, social and economic history, and media studies) that have paradigmatic data representations (textual corpora, structured data, and multimedia). We summarise the lessons learnt from using such ontologies and tools in these domains from a generalisation and reusability perspective.

0
0
0
下載
預覽

最新論文

One of the most important goals of digital humanities is to provide researchers with data and tools for new research questions, either by increasing the scale of scholarly studies, linking existing databases, or improving the accessibility of data. Here, the FAIR principles provide a useful framework as these state that data needs to be: Findable, as they are often scattered among various sources; Accessible, since some might be offline or behind paywalls; Interoperable, thus using standard knowledge representation formats and shared vocabularies; and Reusable, through adequate licensing and permissions. Integrating data from diverse humanities domains is not trivial, research questions such as "was economic wealth equally distributed in the 18th century?", or "what are narratives constructed around disruptive media events?") and preparation phases (e.g. data collection, knowledge organisation, cleaning) of scholars need to be taken into account. In this chapter, we describe the ontologies and tools developed and integrated in the Dutch national project CLARIAH to address these issues across datasets from three fundamental domains or "pillars" of the humanities (linguistics, social and economic history, and media studies) that have paradigmatic data representations (textual corpora, structured data, and multimedia). We summarise the lessons learnt from using such ontologies and tools in these domains from a generalisation and reusability perspective.

0
0
0
下載
預覽
Top