meta data for this page
  •  

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
research [2021/08/21 12:06]
adam 		research [2023/05/02 13:29] (current)
adam
Line 1: Line 1:
  
-=====Recent Research Topics=====+=====Recent Research Topics (Only selected ones)=====
  
 <WRAP column 45% justify> <WRAP column 45% justify>
Line 13: Line 13:
  
 <WRAP column 45% justify> <WRAP column 45% justify>
-=== Timeline Generation === +=== Automatic Timeline Generation=== 
-Timeline summarization generates timelines from news collections for arbitrary queries. For examples, one can generate timeline of covid-19 related events in Austria. In this research we investigate generation of multiple timelines at the same time from underlying document collections rather than single timelines as it has been done so far. In addition, we have also conducted researches on contrastive timeline generation and financial document timeline generation.+Timeline summarization generates timelines from news collections for arbitrary queries. For example, one can generate timeline of covid-19 related events in Austria. In this research we investigate generation of multiple timelines at the same time from underlying document collections rather than single timelines as it has been done so far. In addition, we have also conducted researches on contrastive timeline generation and financial document timeline generation.
  
 {{ wiki:timeline-comparative.png?400x400 }} {{ wiki:timeline-comparative.png?400x400 }}
Line 22: Line 22:
  
 <WRAP column 45% justify> <WRAP column 45% justify>
-=== Novel Access Methods to News Collections === +=== Novel Access Methods to Large News Collections === 
-Access to longitudinal news collections requires novel user-friendly solutions as average users tend to lack contextual information needed to understand the news stories. We propose ranking news articles by their contemporary relevance which is the degree to which the news relate to present, as well as we provide methods for the estimation of news interestingness. Furthermore, we propose various approaches approaches for computing temporal analogy.+Access to longitudinal news collections requires novel user-friendly solutions as average users tend to lack contextual information needed to understand the news stories. We propose ranking news articles by their [[https://adammo12.github.io/adamjatowt/jcdl21m.pdf |contemporary relevance]] which is the degree to which the news relate to present, as well as we provide methods for the estimation of news interestingness. Furthermore, we propose various approaches for computing temporal analogy.
  
 {{ wiki:news-comp.png?300x300 }} {{ wiki:news-comp.png?300x300 }}
Line 31: Line 31:
 <WRAP column 45% justify> <WRAP column 45% justify>
 === Text Readability Estimation=== === Text Readability Estimation===
-Many users have problems with understanding complex texts especially ones that require specialized domain knowledge (e.g., law, medicine) or high cognitive processing. We propose approaches for automatically estimating text difficulty levels. One of the application example can be readability-aware search engine which outputs relevant yet easy-to-read and understandable document for difficult queries or topics.+Many users have problems with understanding complex texts, especially, ones that require knowledge of specialized domain (e.g., law, medicine) or high cognitive processing skills. We propose approaches for automatically estimating text difficulty levels. An example can be seen in the recently released online service for estimating the readability of text in German: [[ https://tinyurl.com/GermanTextReadability|Ablesbarkeitsmesser]]. One of the other application examples for this research can be readability-aware search engine which outputs not only relevant documents but also ones that are easy-to-read and understandable for difficult queries or topics.
  
 {{ wiki:readability-nakatani-method1.png?350x350 }} {{ wiki:readability-nakatani-method1.png?350x350 }}
Line 40: Line 40:
 === Temporal Text Analysis & Understanding=== === Temporal Text Analysis & Understanding===
  
-This research assumes generating diverse temporal estimations for textual content. For example, the examples of estimator computation are automatic creation date estimation, focus date detection, analysis of semantic evolution of words in old texts, frequency estimation of past texts at the time of their creation. Another range of temporal estimators deal with events expressed in text, e.g., estimation of event dates or action continuity and validity prediction (temporal natural language inference).+This research assumes generating diverse temporal estimations for textual content. The examples of such estimator computation are publication date prediction, text focus date detection, or analysis of semantic evolution of words in past texts. Another range of temporal estimators deal with deep understanding of events expressed in text, e.g., estimation of event dates, or prediction of action continuity and validity (temporal natural language inference).
  
 {{ wiki:tem-text-study.png?350x350 }} {{ wiki:tem-text-study.png?350x350 }}
Line 49: Line 49:
 === Domain-specific Business Applications=== === Domain-specific Business Applications===
  
-This research assumes adaptation and application of Natural Language Processing, Information Retrieval and Knowledge Extraction methods to diverse business areas including insurance, economics and law. Examples of these are financial news summarization and timeline generation, risk assessment, international relation prediction or judicial support for conducting trial debates by automatic judge question generation.+This research focuses on adaptation and application of Natural Language Processing, Information Retrieval and Knowledge Extraction methods to diverse business areas including insurance, economics and law. Examples are financial news summarization and timeline generation, risk assessment for insurance, international relation prediction or judicial support for conducting trial debates by judge's question generation.
  
 {{ wiki:future-prediction.png?250x250 }} {{ wiki:future-prediction.png?250x250 }}