Sara Silveira

TM-Gen: A Topic Map Generator from Text Documents

The vast amount of text documents stored in digital format is growing at a frantic rhythm each day. Therefore, tools able to find accurate information searching in natural language information repositories are gaining great interest in recent years. In this context, there are especially interesting tools capable of dealing with large amounts of text information and deriving human-readable summaries. However, one step further is to be able not only to summarize, but to extract the knowledge stored in those texts, and even represent it graphically. In this paper we present an architecture to generate automatically a conceptual representation of knowledge stored in a set of text-based documents. For this purpose we have used the topic maps standard and we have developed a method that combines text mining, statistics, linguistic tools, and semantics to obtain a graphical representation of the information contained therein, which can be coded using a knowledge representation language such as RDF or OWL. The procedure is language-independent, fully automatic, self-adjusting, and it does not need manual configuration by the user. Although the validation of a graphic knowledge representation system is very subjective, we have been able to take advantage of an intermediate product of the process to make a experimental validation of our proposals.

Extracting multi-document summaries with a double clustering approach

This paper presents a method for extractive multi-document summarization that explores a two-phase clustering approach. First, sentences are clustered by similarity, and one sentence per cluster is selected, to reduce redundancy. Then, in order to group them according to topics, those sentences are clustered considering the collection of keywords. Additionally, the summarization process further includes a sentence simplification step, which aims not only to create simpler and more incisive sentences, but also to make room for the inclusion of relevant content in the summary as much as possible.

Combining a double clustering approach with sentence simplification to produce highly informative multi-document summaries

This paper presents a method for extractive multi-document summarization that explores a two-phase clustering approach that, combined with a sentence simplification procedure, aims to generate more useful summaries. First, sentences are clustered by similarity, and one sentence per cluster is selected, to reduce redundancy. Then, in order to group them according to topics, those sentences are clustered considering the collection of keywords. Finally, the summarization process includes a sentence simplification step, which aims not only to create simpler and more incisive sentences, but also to make room for the inclusion of further relevant content in the summary. Evaluation reveals that the approach pursued produces highly informative summaries, containing relevant data and no repeated information.

Using a Double Clustering Approach to Build Extractive Multi-document Summaries

This paper presents a method for extractive multi-document summarization that explores a two-phase clustering approach. First, sentences are clustered by similarity, and one sentence per cluster is selected, to reduce redundancy. Then, in order to group them according to topics, those sentences are clustered considering the collection of keywords that represent the topics in the set of texts. Evaluation reveals that the approach pursued produces highly informative summaries, containing many relevant data and no repeated information.

LX-Center: a center of online linguistic services

This is a paper supporting the demonstration of the LX-Center at ACL-IJCNLP-09. LX-Center is a web center of online linguistic services aimed at both demonstrating a range of language technology tools and at fostering the education, research and development in natural language science and technology.

XisQuê: An Online QA Service for Portuguese

This paper describes XisQue ( http://xisque.di.fc.ul.pt ) an online service for real-time, open-domain question answering (QA) on the Portuguese Web.

Real-Time Open-Domain QA on the Portuguese Web

This paper presents a system for real-time, open-domain question answering on the Web of documents written in Portuguese, prepared to handle factual questions and available as a freely accessible online service. In order to deliver candidate answers to input questions phrased in Portuguese, this system resorts to a number of shallow processing tools and question answering techniques that are specifically geared to cope with the Portuguese language.

Uncovering Discourse Relations to Insert Connectives between the Sentences of an Automatic Summary

This paper presents a machine learning approach to find and classify discourse relations between two unseen sentences. It describes the process of training a classifier that aims to determine (i) if there is any discourse relation among two sentences, and, if a relation is found, (ii) which is that relation. The final goal of this task is to insert discourse connectives between sentences seeking to enhance text cohesion of a summary produced by an extractive summarization system for the Portuguese language.

Sentence Reduction Algorithms to Improve Multi-document Summarization

Multi-document summarization aims to create a single summary based on the information conveyed by a collection of texts. After the candidate sentences have been identified and ordered, it is time to select which will be included in the summary. In this paper, we describe an approach that uses sentence reduction, both lexical and syntactic, to help improve the compression step in the summarization process. Three different algorithms are proposed and discussed. Sentence reduction is performed by removing specific sentential constructions conveying information that can be considered to be less relevant to the general message of the summary. Thus, the rationale is that sentence reduction not only removes expendable information, but also makes room for further relevant data in a summary.