Interactive Ambiguity Resolution of Named Entities in Fictional Literature

Stoffel, Florian; Jentner, Wolfgang; Behrisch, Michael; Fuchs, Johannes; Keim, Daniel A.

doi:10.1111/cgf.13179

Cited by 8 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Visualization for NLP and CL Creating and using embeddings in NLP and CL is crucial for representing and capturing the context and content of words, phrases, sentences, and documents. VA + embedding techniques in this set focus on four themes: exploring the semantics and contextualization of embedding spaces [CTL18,LBT * 18,EAKC * 20,MWZ19,SSKEA21, GHM21, BN21, BCS22,VMZL22,LWZ * 23,MM23], active learning and interpretation for language models [LCSEK19, TWB * 20, SH20, ARCL21, LXW * 21, SKB * 21, SCR * 23], data‐driven information retrieval [CWDH09,BMS17,ZSHL18,KOK * 18,DMdO19, RSBV21, PdSP * 22, JWC * 23], and annotation tools [SJB * 17, BNL * 18,PKL * 18,MWJ22].…”

Section: Categorization Of Va + Embedding Approachesmentioning

confidence: 99%

VA + Embeddings STAR: A State‐of‐the‐Art Report on the Use of Embeddings in Visual Analytics

Huang

Witschard

Kucher

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Over the past years, an increasing number of publications in information visualization, especially within the field of visual analytics, have mentioned the term “embedding” when describing the computational approach. Within this context, embeddings are usually (relatively) low‐dimensional, distributed representations of various data types (such as texts or graphs), and since they have proven to be extremely useful for a variety of data analysis tasks across various disciplines and fields, they have become widely used. Existing visualization approaches aim to either support exploration and interpretation of the embedding space through visual representation and interaction, or aim to use embeddings as part of the computational pipeline for addressing downstream analytical tasks. To the best of our knowledge, this is the first survey that takes a detailed look at embedding methods through the lens of visual analytics, and the purpose of our survey article is to provide a systematic overview of the state of the art within the emerging field of embedding visualization. We design a categorization scheme for our approach, analyze the current research frontier based on peer‐reviewed publications, and discuss existing trends, challenges, and potential research directions for using embeddings in the context of visual analytics. Furthermore, we provide an interactive survey browser for the collected and categorized survey data, which currently includes 122 entries that appeared between 2007 and 2023.

show abstract

Section: Categorization Of Va + Embedding Approachesmentioning

confidence: 99%

VA + Embeddings STAR: A State‐of‐the‐Art Report on the Use of Embeddings in Visual Analytics

Huang

Witschard

Kucher

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…The final approach includes custom visualizations whose main motivation is an uncertainty. Working with literary scholars, Stoffel et al [111] created a visualization tool directly for disambiguating entities in book character networks (Figure 7-left). Alex et al motivate their work, Palimpsest, a mixed human-automated text mining visualization tool that helps identify literary works set in Edinburgh, as a way to alleviate uncertainty appearing from computational classification [2].…”

Section: Representing Uncertainty In the Visualizationsmentioning

confidence: 99%

“…Dedicated uncertainty visualizations. Left -A custom visualization that supports disambiguation in named entity recognition results[111]. Right -A dedicated visualization approach that supports working with conflicting data of translation texts[64].…”

mentioning

confidence: 99%

Communicating Uncertainty in Digital Humanities Visualization Research

Panagiotidou

Lamqaddam

Poblome

et al. 2022

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Due to their historical nature, humanistic data encompass multiple sources of uncertainty. While humanists are accustomed to handling such uncertainty with their established methods, they are cautious of visualizations that appear overly objective and fail to communicate this uncertainty. To design more trustworthy visualizations for humanistic research, therefore, a deeper understanding of its relation to uncertainty is needed. We systematically reviewed 126 publications from digital humanities literature that use visualization as part of their research process, and examined how uncertainty was handled and represented in their visualizations. Crossing these dimensions with the visualization type and use, we identified that uncertainty originated from multiple steps in the research process from the source artifacts to their datafication. We also noted how besides known uncertainty coping strategies, such as excluding data and evaluating its effects, humanists also embraced uncertainty as a separate dimension important to retain. By mapping how the visualizations encoded uncertainty, we identified four approaches that varied in terms of explicitness and customization. This work contributes with two empirical taxonomies of uncertainty and it's corresponding coping strategies, as well as with the foundation of a research agenda for uncertainty visualization in the digital humanities. Our findings further the synergy among humanists and visualization researchers, and ultimately contribute to the development of more trustworthy, uncertainty-aware visualizations.

show abstract

“…The critical question is how much automation should be used, how far it should go, and how it should relate to human investigators' activities [99]. What operations need to be supported and guided, for example, by recommending alternative search terms or related individuals, and what agency should the analyst retain in interpreting the machine output?…”

Section: Ethical Challenges For Communication Analysismentioning

confidence: 99%

Promoting Ethical Awareness in Communication Analysis: Investigating Potentials and Limits of Visual Analytics for Intelligence Applications

Fischer,

Hirsbrunner,

Jentner

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Digital systems for analyzing human communication data have become prevalent in recent years. This may be related to the increasing abundance of data that can be harnessed but can hardly be managed manually. Intelligence analysis of communications data in investigative journalism, criminal intelligence, and law present particularly interesting cases, as they must take into account the often highly sensitive properties of the underlying operations and data. At the same time, these are areas where increasingly automated, sophisticated approaches and tailored systems can be particularly useful and relevant, especially in terms of Big Data manageability.However, by the shifting of responsibilities, this also poses dangers . In addition to privacy concerns, these dangers relate to uncertain or poor data quality, leading to discrimination and potentially misleading insights. Other problems relate to a lack of transparency and traceability, making it difficult to accurately identify problems and determine appropriate remedial strategies.Visual analytics combines machine learning methods with interactive visual interfaces to enable human sense-and decision-making. This technique can be key for designing and operating meaningful interactive communication analysis systems that consider these ethical challenges. In this interdisciplinary work, a joint endeavor of computer scientists, ethicists, and scholars in Science & Technology Studies, we investigate and evaluate opportunities and risks involved in using Visual analytics approaches for communication analysis in intelligence applications in particular. We introduce, at first, the common technological systems used in communication analysis, with a special focus on intelligence analysis in criminal investigations, further discussing the domain-specific ethical implications, tensions, and risks involved. We then make the case of how tailored Visual Analytics approaches may reduce and mitigate the described problems, both theoretically and through practical examples. Offering interactive analysis capabilities and what-if explorations while facilitating guidance, provenance generation, and bias awareness (through nudges, for example) can improve analysts' understanding of their data, increasing trustworthiness, accountability, and generating knowledge. We show that finding Visual Analytics design solutions for ethical issues is not a mere optimization task with an ideal final solution. Design solutions for specific ethical problems (e.g., privacy) often trigger new ethical issues (e.g., accountability) in other areas. Balancing out and negotiating these trade-offs has, as we argue, to be an integral aspect of the system design process from the outset. Finally, our work identifies existing gaps and highlights research opportunities, further describing how our results can be transferred to other domains. With this contribution, we aim at informing more ethically-aware approaches to communication analysis in intelligence operations.CCS Concepts: • Computing methodologies → Visua...

show abstract

Interactive Ambiguity Resolution of Named Entities in Fictional Literature

Cited by 8 publications

References 35 publications

VA + Embeddings STAR: A State‐of‐the‐Art Report on the Use of Embeddings in Visual Analytics

VA + Embeddings STAR: A State‐of‐the‐Art Report on the Use of Embeddings in Visual Analytics

Communicating Uncertainty in Digital Humanities Visualization Research

Promoting Ethical Awareness in Communication Analysis: Investigating Potentials and Limits of Visual Analytics for Intelligence Applications

Contact Info

Product

Resources

About