Delia Rusu

Document Visualization Based on Semantic Graphs

In this paper, we present a document visualization technique for data analysis based on the semantic representation of text in the form of a directed graph, referred to as semantic graph. It is derived using natural language processing as follows. Firstly subject– verb – object triplets are automatically extracted from the Penn Treebank parse tree obtained for each sentence in the document. Secondly, the triplets are further enhanced by linking them to their corresponding co-referenced named entity, by resolving pronominal anaphors as well as attaching the associated WordNet synset. Starting from the documents semantic graph and the list of extracted triplets we automatically generate the document summary, for which we also derive the semantic representation.

Visual analysis of documents with semantic graphs

In this paper, we present a technique for visual analysis of documents based on the semantic representation of text in the form of a directed graph, referred to as semantic graph. This approach can aid data mining tasks, such as exploratory data analysis, data description and summarization. In order to derive the semantic graph, we take advantage of natural language processing, and carry out a series of operations comprising a pipeline, as follows. Firstly, named entities are identified and co-reference resolution is performed; moreover, pronominal anaphors are resolved for a subset of pronouns. Secondly, subject -- predicate -- object triplets are automatically extracted from the Penn Treebank parse tree obtained for each sentence in the document. The triplets are further enhanced by linking them to their corresponding co-referenced named entity, as well as attaching the associated WordNet synset, where available. Thus we obtain a semantic directed graph composed of connected triplets. The documents semantic graph is a starting point for automatically generating the document summary. The model for summary generation is obtained by machine learning, where the features are extracted from the semantic graph structure and content. The summary also has an associated semantic representation. The size of the semantic graph, as well as the summary length can be manually adjusted for an enhanced visual analysis. We also show how to employ the proposed technique for the Visual Analytics challenge.

DiversiNews: Surfacing Diversity in Online News

For most events of at least moderate significance, there are likely tens, often hundreds or thousands of online articles reporting on it, each from a slightly different perspective. If we want to understand an event in depth, from multiple perspectives, we need to aggregate multiple sources and understand the relations between them. However, current news aggregators do not offer this kind of functionality. As a step towards a solution, we propose DiversiNews, a real-time news aggregation and exploration platfom whose main feature is a novel set of controls that allow users to contrast reports of a selected event based on topical emphases, sentiment differences and/or publisher geolocation. News events are presented in the form of a ranked list of articles pertaining to the event and an automatically generated summary. Both the ranking and the summary are interactive and respond in real time to user’s change of controls. We validated the concept and the user interface through user tests with positive results.

Enhanced Web Page Content Visualization with Firefox

This paper aims at presenting how natural language processing and machine learning techniques can help the internet surfer to get a better overview of the pages he is reading. The proposed demo is a Firefox extension which can show a semantic graph of the text in the page that is currently loaded in the browser. The user can also get a summary of the web page she is looking at by choosing to display only the more important nodes in the semantic graph representation of the document, where importance of the nodes is obtained by machine learning techniques.

Measuring concept similarity in ontologies using weighted concept paths

Semantic similarity and relatedness between concepts have been extensively studied in different areas ranging from psychology to computational linguistics. In this paper we address the problem of determining the similarity between concepts defined in a knowledge source such as an ontology. The focus is measuring similarity between concepts from the same ontology. We propose a concept similarity algorithm based on geometric models for representing concepts and relationships, which can be applied to different types of ontologies. The key idea is the concept weighting scheme which allows for quantifying the degree of abstractness of concepts. The evaluation settings involving two ontologies validate and highlight the advantages and disadvantages of the proposed approach. Using the proposed measure, which closely resembles the human judgment of similarity, we can reliably recreate predefined concept clusters, and generate more informative concept paths.

AnswerArt: contextualized question answering

The focus of this paper is a question answering system, where the answers are retrieved from a collection of textual documents. The system also includes automatic document summarization and document visualization by means of a semantic graph. The information extracted from the documents is stored as subject-predicate-object triplets, and the indexed terms are expanded using Cyc, a large common sense ontology.

Text stream processing

The aim of this tutorial is to present an overview of text stream processing starting with a description and properties of text streams, and continuing with a series of text processing techniques and their applicability to text streams. Among the text processing techniques we are going to describe entity extraction and resolution, event and fact extraction, word sense disambiguation, sentiment analysis, summarization, social network analysis, all in the context of text streams. The goal is to present the list of problems and challenges arising when processing text streams and to show how they can be approached using text mining, natural language processing and semantic analysis techniques and tools. The tutorial will describe available approaches and show some demos on text data streams, using publicly available tools.