Natural language interactions enhanced by data visualization to explore insurance claims and manage risk

Islam, Rafiqul; Razzak, Muhammad Imran; Wang, Xianzhi; Tilocca, Peter; Xu, Guandong

doi:10.1007/s10479-021-04465-7

Cited by 5 publications

(4 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The visualization results of NL4DV are specified with Vega-Lite grammar (Figure 4A), which is popular in the field of NLI [5], [23], [24], [28], [29], [30], [32], [52]. We leverage provenance to depict the three aspects of the visualization process and introduce the Provenance Generator, which consists of three major components to construct the visualization provenance from the Vega-Lite grammar, select representative sample data for demonstration, and apply visual cues to highlight the changes in provenance.…”

Section: Provenance Generatormentioning

confidence: 99%

“…Our work is based on NL4DV, a typical toolkit following the general pipeline of NLI [1], [4], and the major components of our system (i.e., Provenance Generator, interactive widgets, Hint Generator) are independent of the specific details of NLI algorithms and can be directly applied to the existing NLIs. The Provenance Generator reveals the visualization process based on the Vega-Lite specification, which is widely used by many NLIs [5], [23], [24], [28], [29], [30], [32], [52]. The Hint Generator integrates a set of well-known rules [4], [5], [12] to detect problems in the query and can be extended to support more scenarios in different application domains.…”

Section: Generalizabilitymentioning

confidence: 99%

See 1 more Smart Citation

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

Feng

Wang

Pan

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint Generator to provide query revision hints based on the analysis of user queries and interactions. Two usage scenarios of XNLI and a user study verify the effectiveness and usability of the system. Results suggest that XNLI can significantly enhance task accuracy without interrupting the NLI-based analysis process.

show abstract

Section: Provenance Generatormentioning

confidence: 99%

Section: Generalizabilitymentioning

confidence: 99%

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

Feng

Wang

Pan

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…In addition to the above, Islam et al [15] investigated how interactive visualisations could be used for insurance claims analysis. This research informs that guidelines have been formed to help the insurance industry incorporate this into practice.…”

Section: Literature Reviewmentioning

confidence: 99%

Utilising Big Data Analytics in the Insurance Industry for Optimal Business Insight: A Literature Review

Pye,

Olajide

2023

IJI

View full text Add to dashboard Cite

Organisations and insurance companies are not utilising business data and analytical methods to gain full advantage of accurate representation of risk, which can lead to further risk such as underinsurance, overpriced policies, and inaccurate claims assessment. Many companies organise their own insurance and risk management internally and rely on external experts such as insurance companies, brokers, and underwriters to help determine requirements. As part of this set up, there is a reliance on data derived from the organisation to inform policy placement, pricing of insurance policies and to accurately represent risk. The nature for enhancing the operational efficiency of insurance products using Big Data Analytics (BDA) is found to be a common concept in the insurance industry. The research work relating to insurance risks and cyber security is still in its infancy. Therefore, the research aim is to investigate how best to derive business insight from the insurance and risk division of an organisation using Big Data Analytics (BDA). The research considered security metrics for risk, control and mitigation based on the organisation's reaction to cyber risk for data accuracy. This paper reviews research previously conducted in the area with the aim of understanding which Big Data Analytics (BDA) methods are currently used and in which areas of the insurance industry. The findings show that Big Data Analytics (BDA) methods such as predictive analytics, artificial intelligence, machine learning and random forest regression are utilised in areas of insurance such as underwriting, claims and pricing.

show abstract

“…Unstructured text poses a challenge in information extraction and retrieval as it is not purely data but is almost always described in the form of natural language, often with associated non-textual elements such as emoji, images, tables, graphs, and emotions. However, unstructured text is vital due to its volume and has become a primary source of information for many information systems (Islam et al, 2022). As a result, extracting knowledge from unstructured text is crucial to constructing up-to-date KGs with the latest information (Bizer et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Doc‐KG: Unstructured documents to knowledge graph construction, identification and validation with Wikidata

Salman,

Haller,

Méndez

et al. 2024

Expert Systems

View full text Add to dashboard Cite

The exponential growth of textual data in the digital era underlines the pivotal role of Knowledge Graphs (KGs) in effectively storing, managing, and utilizing this vast reservoir of information. Despite the copious amounts of text available on the web, a significant portion remains unstructured, presenting a substantial barrier to the automatic construction and enrichment of KGs. To address this issue, we introduce an enhanced Doc‐KG model, a sophisticated approach designed to transform unstructured documents into structured knowledge by generating local KGs and mapping these to a target KG, such as Wikidata. Our model innovatively leverages syntactic information to extract entities and predicates efficiently, integrating them into triples with improved accuracy. Furthermore, the Doc‐KG model's performance surpasses existing methodologies by utilizing advanced algorithms for both the extraction of triples and their subsequent identification within Wikidata, employing Wikidata's Unified Resource Identifiers for precise mapping. This dual capability not only facilitates the construction of KGs directly from unstructured texts but also enhances the process of identifying triple mentions within Wikidata, marking a significant advancement in the domain. Our comprehensive evaluation, conducted using the renowned WebNLG benchmark dataset, reveals the Doc‐KG model's superior performance in triple extraction tasks, achieving an unprecedented accuracy rate of 86.64%. In the domain of triple identification, the model demonstrated exceptional efficacy by mapping 61.35% of the local KG to Wikidata, thereby contributing 38.65% of novel information for KG enrichment. A qualitative analysis based on a manually annotated dataset further confirms the model's excellence, outshining baseline methods in extracting high‐fidelity triples. This research embodies a novel contribution to the field of knowledge extraction and management, offering a robust framework for the semantic structuring of unstructured data and paving the way for the next generation of KGs.

show abstract

Natural language interactions enhanced by data visualization to explore insurance claims and manage risk

Cited by 5 publications

References 57 publications

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

Utilising Big Data Analytics in the Insurance Industry for Optimal Business Insight: A Literature Review

Doc‐KG: Unstructured documents to knowledge graph construction, identification and validation with Wikidata

Contact Info

Product

Resources

About