Abstract not found

In this paper we propose a methodology for sentiment analysis of figurative language which applies Word Sense Disambiguation and, through an n-gram graph based method, assigns polarity to word senses. Polarity assigned to senses, combined with contextual valence shifters, is exploited for further assigning polarity to sentences, using Hidden Markov Models. Evaluation results using the corpus of the Affective Text task of SemEval’07, are presented together with a comparison with other state-of-the-art methods, showing that the proposed method provides promising results, and positive evidence supporting our conjecture: figurative language conveys sentiment. 1

This work reports on research conducted on the domain of multi-document summarization using background knowledge. The research focuses on summary evaluation and the implementation of a set of generic use tools for NLP tasks and especially for automatic summarization. Within this work we formalize the n-gram graph representation and its use in NLP tasks. We present the use of n-gram graphs for the tasks of summary evaluation, content selection, novelty detection and redundancy removal. Furthermore, we present a set of algorithmic constructs and methodologies, based on the notion of n-gram graphs, that aim to support meaning extraction and textual quality quantification.

Abstract—Real-word entities can be mapped to unique entity identifiers through an Entity Name System (ENS), to systematically support the re-use of these identifiers and disambiguate references to real world entities in the Web. An entity subscription service informs subscribed users of changes in the descriptive data of an entity, which is a set of attribute name-value pairs. We study the design, implementation and application of an adaptable push-policy subscription service, within a large-scale ENS. The subscription system aims to deliver ranked descriptions of the changes on entities, following user preferences through a feedback-driven adaptation process. The adaptation is based on both the content and the type of each entity change. We evaluate the learning curve of the system and the utility of the content-type discrimination. The experiments demonstrate good results, especially in the system’s content-aware adaptation aspect. Keywords-Adaptive systems; Artificial intelligence; User modeling

Abstract. Within this article, we sketch the set of generic tools we have devised and used within the summarization process and the domain of summary evaluation, focusing on how the tools were used within the TAC 2008 summarization update challenge. The tools have a common underlying theory and provide utility in various aspects of the Natural Language Processing domain. Within this study we elaborate on query expansion, content matching and filtering, redundancy removal as well as summary evaluation. 1.

Within this article, we present the application of the AutoSummENG method within the TAC 2009 AESOP challenge. We further offer an alternative to the original AutoSummENG method, which uses an additional operator of the n-gram graph framework to represent a set of documents with a single, merged graph. This alternative shows promising effectiveness and suggests that n-gram graphs and their operators can constitute an effective and updatable text representation method.

This paper describes a summarization system that aims to provide a set of languageindependent and generic methods for generating extractive summaries. The proposed methods are realized as operators to a generic character n-gram graph representation of texts, towards the selection of content and removal of redundancy. This work defines the set of generic operators upon n-gram graphs and proposes a number of ways for using these operators within the summarization process. The experimental results, performed upon widely used corpora from the Document Understanding and the Text Analysis Conferences, are promising, providing evidence for the potential of the generic methods introduced. 2 George Giannakopoulos, George Vouros, Vangelis Karkaletsis 1

This presentation offers an introduction into the AutoSummENG summary evaluation method, based on n-gram graphs. It further discusses the possibility to combine summary system evaluators into a combined evaluator and present early experiments.

In the past, we have succesfully used machine learning approaches for sentiment analysis. In the course of those experiments, we observed that our machine learning method, although able to cope well with figurative language could not always reach a certain decision about the polarity orientation of sentences, yielding erroneous evaluations. We support the conjecture that these cases bearing mild figurativeness could be better handled by a rule-based system. These two systems, acting complementarily, could bridge the gap between machine learning and rule-based approaches. Experimental results using the corpus of the Affective Text Task of SemEval ’07, provide evidence in favor of this direction. 1.

Abstract. The presented work studies textual summaries, aiming to detect the qualities of human multi-document summaries, in contrast to automatically extracted ones. The measured features are based on a generic statistical regularity measure, named Symbol Sequence Statistical Regularity (SSSR). The measure is calculated over both character and word n-grams of various ranks, given a set of human and automatically extracted multi-document summaries from two different corpora. The results of the experiments indicate that the proposed measure provides enough distinctive power to discriminate between the human and non-human summaries. The results hint on the qualities a human summary holds, increasing intuition related to how a good summary should be generated. 1