Natural Language Understanding for Information Fusion

Shapiro, Stewart; Schlegel, Daniel R.

doi:10.1007/978-3-319-22527-2_2

Cited by 5 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays SNePS is a part of GLAIR, a multi-layered cognitive architecture for "embodied agents operating in real, virtual, or simulated environments containing other agents" (Shapiro, Bona 2010: 307). It has been used in a variety of tasks, including contextual vocabulary acquisition (Rapaport, Ehrlich 2000), natural language understanding for information fusion (Shapiro, Schlegel 2013), research on conceptualization and commonsense ontologies (Gruber 1992), metacognition (Shapiro et al 2007), embodied, and natural-language usage.…”

Section: Cognitive Modeling Of Languagementioning

confidence: 99%

Between Language and Consciousness: Linguistic Qualia, Awareness, and Cognitive Models

Konderak

2016

Studies in Logic, Grammar and Rhetoric

View full text Add to dashboard Cite

The main goal of the paper is to present a putative role of consciousness in language capacity. The paper contrasts the two approaches characteristic for cognitive semiotics and cognitive science. Language is treated as a mental phenomenon and a cognitive faculty (in contrast to approaches that define language as a primarily social phenomenon). The analysis of language activity is based on the Chalmers’ (1996) distinction between the two forms of consciousness: phenomenal (simply “consciousness”) and psychological (“awareness”). The approach is seen as an alternative to phenomenological analyses typical for cognitive semiotics. Further, a cognitive model of the language faculty is described. The model is implemented in SNePS/GLAIR architecture and based on GATN grammar and semantic networks as a representation formalism. The model - reflecting traditionally distinguished linguistic structures (Jackendoff 2002: 198) - consists of phonological, syntactic, and semantic modules. I claim that the most important role in the phenomenon of language (and in explanations thereof) is played by psychological consciousness. Phenomenal consciousness accompanies various stages of language functioning (e.g. linguistic qualia), but is not indispensable in explanations of the language faculty.

show abstract

Section: Cognitive Modeling Of Languagementioning

confidence: 99%

Between Language and Consciousness: Linguistic Qualia, Awareness, and Cognitive Models

Konderak

2016

Studies in Logic, Grammar and Rhetoric

View full text Add to dashboard Cite

show abstract

“…At present, there is much work in various types of text analytics going on, some of it with a focus on the needs of fusion algorithms. One example of such a focused system is the Tractor system [10], developed for text understanding in situation assessment problems. Analogously, soft data processing has been proposed in counterinsurgency examples, such as [11].…”

Section: Previous Workmentioning

confidence: 99%

Multi-level Fusion of Hard and Soft Information for Intelligence

Biermann

García

Krenc³

et al. 2016

Context-Enhanced Information Fusion

View full text Add to dashboard Cite

Driven by the underlying need for an as yet undeveloped framework for fusing heterogeneous data and information at different semantic levels coming from both sensory and human sources, we present some results of the research conducted within the NATO Research Task Group IST-106/RTG-051 on “Information Filtering and Multi Source Information Fusion.” As part of this ongoing effort, we discuss here a first outcome of our investigation on multi-level fusion. It deals with removing the first hurdle between data/information sources and processes being at different levels: representation. Our contention here is that a common representation and description framework is the premise for enabling processing overarching different semantic levels. To this end, we discuss here the use of the Battle Management Language (BML) as a way (“lingua franca”) to encode sensor- and text-based data and a priori and contextual knowledge, both as hard and soft data. We here expand on our previous works [1, 2] further detailing and exemplifying the use of BML and clarifying aspects related to the use of contextual information and the exploitation of uncertain soft input along with sensor readings

show abstract

“…In order to make sense of complex scenarios to detect maritime threats, and for situational awareness in general, it has been increasingly recognised that the fusion of data relating to physical movement, such as that generated by physical sensors (i.e., hard data, which has been extensively studied for sensor data fusion), is not sufficient, but requires all available information, including data provided by humans and intelligence (i.e., soft data) as well as other operational and contextual information [5], [6]. Efforts to incorporate soft data into fusion frameworks for situational awareness have considered various types of soft data, including extant textual data in a structured or logical format [7], [8]; text annotations associated with hard data that potentially provide additional attributes for the relevant entities [9]; certain entities and concepts of interest [10]- [14] and a few simple relations between them [15] extracted from short human statements [12], social network data [13], semi-structured synthesised reports [14], maritime incident reports [10] and news articles [15]; and also semantic knowledge constructed from natural language text (albeit, without taking into account the uncertainty associated with the extracted knowledge) [16], [17].…”

mentioning

confidence: 99%