An NLP-based Question Answering Framework for Spatio-Temporal Analysis and Visualization

Yin, Zhengcong; Zhang, Chong; Goldberg, Daniel W.; Prasad, Sathya

doi:10.1145/3318236.3318240

Cited by 13 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The interpretation of the geographic analysis aims to translate the geographic question in natural language into machine-understandable geographic analysis tasks with identified methods or tools needed for completing the specific geographic analysis. Natural language process and semantic web (Gao and Goodchild 2013;Scheider, Ballatore, and Lemmens 2019;Yin et al 2019) are used to relate the question asked in natural language with geographic analysis tools. For some simple questions, the questions in natural language can be directly interpreted into analysis tasks.…”

Section: Existing Effortsmentioning

confidence: 99%

Next generation of GIS: must be easy

et al. 2020

View full text Add to dashboard Cite

Existing GIS software mainly target at expert users and do not sufficiently integrate resources for efficient computing. They are difficult for non-experts to use and are often slow in completing the complicated geographic analysis. To address these problems, future generation of GIS software must be 'easy'. By 'easy' we mean 'easy to use' and 'easy to compute'. 'Easy to use' means that software system should be goal-oriented, rather than the currently procedure-oriented doctrine. The goal-oriented will relieve users, particularly novice users, the burden of knowing the exact commands and their sequences to perform for achieving the goal they want to achieve. 'Easy to compute' means that implementation of GIS analytical functionality should be able to utilize the high-performance computing infrastructures for complicated geographic analysis. Two case studies, one in digital soil mapping and the other in digital terrain analysis, are presented to illustrate the meaning of 'easy'. We believe that the future generations of GIS platforms should be goaldriven, intelligent, high-performance computing enabled, easily accessible, and participatory. It allows anyone to participate in geo-computation at anywhere and anytime.

show abstract

Section: Existing Effortsmentioning

confidence: 99%

Next generation of GIS: must be easy

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The first one is that human questions are complex and diverse, so this type is more difficult to apply to open domain questions. [80], [81]. The second is that the accuracy of open domain questions tends to be low [82], [83].…”

Section: Recommendation Systemmentioning

confidence: 99%

A Study of Optimizing Search Engine Results Through User Interaction

Chen

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose a method for optimizing search engine results based on user interaction. This method generates different search results mainly through the user's operation on different search topics. There are two main differences between our method and the traditional personalized search method: personal privacy and storage space. First, traditional personal search methods need to record search and click records for individual users. However, these records have great personal privacy issues for users; especially in recent years, there have been personal privacy leaks that occurred in many large online companies (such as Facebook and Yahoo). Secondly, because different users need to record their own search records, the size of the storage space is closely related to the number of users and the amount of search records stored. However, the sum of individual users' search and click records is a huge storage space in today's Internet environment. To avoid these two issues for traditional personalized search methods, this study proposes a storage-free approach based on individual users operating on different search topics. In general, in addition to avoiding personal privacy and storage space issues, our method can also achieve optimal linear time in generating personalized search results. INDEX TERMS Document clustering, machine learning, natural language processing, personalized topic search, user log.

show abstract

“…Creating feature vectors of words has made the process of integrating textual data into the machine and deep learning models easier. Hence, several NLP applications have been flourished since then, such as sentiment analysis [2], question answering [3], information retrieval [4], and others [5]. Developing a word embedding model requires training on large datasets, where multiple patterns of representation can be captured.…”

Section: Introductionmentioning

confidence: 99%

AltibbiVec: A Word Embedding Model for Medical and Health Applications in the Arabic Language

Habib¹,

Faris²,

Alomari³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In recent years, the utilization of natural language processing (NLP) and Machine Learning (ML) techniques in clinical decision support systems have shown their ability in improving and automating the diagnosis process and reduce the potential for clinical errors. NLP in the Arabic language is more intricate due to several limitations, such as the lack of datasets and analytical resources compared to other languages like English. However, a clinical decision support system in the Arabic context is of significant importance. A fundamental process in NLP is extracting features from textual data via text embedding. Word embedding is a representation of words in a numeric format that encodes the statistic, semantic, or context information. Building a neural word embedding model requires hundreds of thousands of data instances to find hidden patterns of relationships within sentences. Essentially, extracting relevant and informative features promotes the performance of the learning algorithms. The objective of this paper is to propose an Arabic neural-based word embedding model in the medical and healthcare context (called "AltibbiVec"). Around 1.5 million medical consultations and questions are used to train the embedding model. Three different embedding models are developed and compared, which are based on Word2Vec, FastText, and GloVe. The trained models are evaluated by different criteria, including the word clustering and the similarity of words. Besides, they are evaluated by performing a specialty-based question classification. Word2Vec and FastText capture sufficiently the semantics of text more than GloVe.

show abstract

An NLP-based Question Answering Framework for Spatio-Temporal Analysis and Visualization

Cited by 13 publications

References 8 publications

Next generation of GIS: must be easy

Next generation of GIS: must be easy

A Study of Optimizing Search Engine Results Through User Interaction

AltibbiVec: A Word Embedding Model for Medical and Health Applications in the Arabic Language

Contact Info

Product

Resources

About