A Graph Database Model for Knowledge Extracted from Place Descriptions

Chen, Hao; Vasardani, Maria; Winter, Stephan; Tomko, Martin

doi:10.20944/preprints201804.0202.v1

Cited by 9 publications

(37 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatial language is a field that focuses on the spatial descriptions of objects and their connections in a particular environment. The use of machine learning for spatial language processing seems to be helpful and has already been used to extract local references and spatial relationships (Chen et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

“…The term locale is tied to experience, affordance, and functionality (Purves et al, 2019). When a place is functionally different from its surroundings, sense of place arises (Chen et al, 2018). However, Cresswell has considered place as a container of four elements, including the previous three aspects and another aspect called practice (Cresswell, 2009, 2011).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A comparative assessment of machine learning methods in extracting place functionality from textual content

Karimi

Mesgari

Purves

2022

Transactions in GIS

View full text Add to dashboard Cite

Places are usually ambiguous and context dependent. Place functionality as a context in place descriptions is one of the prominent and distinguishing features of place. Today, due to the rapid growth of the Internet and social networks, users usually share place-based information. Among the types of information, user-generated textual content is not usually shared in a specific structure. This article aims to extract place functionality using analysis of user-generated textual contents shared by users. For this purpose, we try to extract and predict the place functionality through the whole user reviews as well as only the action verbs expressed in the reviews. In this research, series of comparative experiments was conducted to highlight the influence of action verbs on the prediction of place functionality and to evaluate the predictability across different natural language processing (NLP) methods. We compare the efficiency of three NLP methods in selecting and extracting features, as well as different machine learning text classifier methods to predict place functionality. Evaluation results show that using the whole text of the review can extract place functionality better than using only the action verbs. Also, the bag-of-words feature extraction method performs better than the two embedding methods. Among text classification algorithms, although the multinomial naïve Bayes method is the fastest method, the support vector machine method is more accurate than all other methods, while the execution time of the algorithm is longer. In addition, among

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A comparative assessment of machine learning methods in extracting place functionality from textual content

Karimi

Mesgari

Purves

2022

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…On the other hand, researchers have also proposed some new graph databases, such as TigerGraph [8] , SeQuery [9] , GraphSE2 [10] , Graphflow [11] , etc., they often adopt different solutions to solve different practical application problems. Reference [12] implements a location graph model based on a graph database, which is used to model the location according to the description information of the place. On this basis, the functions of location matching, reasoning and query are realized.…”

Section: Related Workmentioning

confidence: 99%

An edge-aware-oriented semantic association retrieval method for industrial data

Liu

Zhang²,

Xiao³

2022

6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022)

View full text Add to dashboard Cite

The development of the Industrial Internet has caused a change that traditional Internet technologies gradually sink into the field of industrial manufacturing. Due to the high degree of business coupling at the edge of industrial production, the relationships between the data are complex and difficult to comprehensively analyze and apply. This paper proposes a data semantic association retrieval method for industrial data at the industrial edge. Firstly, the framework of semantic association retrieval of industrial data is established, and then the construction method of inverted table in association retrieval is explained, including the formation method of keyword set and concept set, and the algorithm for realizing semantic association retrieval is given. The algorithm is verified in the actual scene of the test production line, and the results show that the algorithm in this paper is feasible and effective in relational retrieval.

show abstract

“…Based on this assumption and the available information, the specific form of answer can be derived using a SPARQL query template (Query 1). While the structure of a suitable knowledge base for this purpose has been studied before by Chen, Vasardani, Winter, and Tomko (2018), no such knowledge base is yet available with the definitions of type, scale and prominence as used in this study. Hence, the translation is only demonstrated here using the introductory example 9 .…”

Section: Demonstration: From Generic To Specificmentioning

confidence: 99%

Templates of generic geographic information for answering where-questions

Hamzei,

Winter,

Tomko

2021

Preprint

Self Cite

View full text Add to dashboard Cite

In everyday communication, where-questions are answered by place descriptions. To answer where-questions automatically, computers should be able to generate relevant place descriptions that satisfy inquirers' information needs. Human-generated answers to where-questions constructed based on a few anchor places that characterize the location of inquired places. The challenge for automatically generating such relevant responses stems from selecting relevant anchor places. In this paper, we present templates that allow to characterize the human-generated answers and to imitate their structure. These templates are patterns of generic geographic information derived and encoded from the largest available machine comprehension dataset, MS MARCO v2.1. In our approach, the toponyms in the questions and answers of the dataset are encoded into sequences of generic information. Next, sequence prediction methods are used to model the relation between the generic information in the questions and their answers. Finally, we evaluate the performance of predicting templates for answers to where-questions. KEYWORDS question answering; notion of place; scale; prominenceThis where-question is answered using a place description -a description that characterizes the location of interest (Putney Bridge) based on a few anchor places (River Thames and London). Place descriptions, however, are not the only way to answer where-questions. Where-questions can also be answered via other representations such as maps or sketches (Church, Neumann, Cherubini, & Oliver, 2010). Invariant to the chosen representation, the answers localize the place in question based on its spatial relationships with chosen anchor places (Couclelis, Golledge, Gale, & Tobler, 1987).

show abstract

A Graph Database Model for Knowledge Extracted from Place Descriptions

Cited by 9 publications

References 44 publications

A comparative assessment of machine learning methods in extracting place functionality from textual content

A comparative assessment of machine learning methods in extracting place functionality from textual content

An edge-aware-oriented semantic association retrieval method for industrial data

Templates of generic geographic information for answering where-questions

Contact Info

Product

Resources

About