Guillermo Garrido

WHAD: Wikipedia historical attributes data

This paper describes the generation of temporally anchored infobox attribute data from the Wikipedia history of revisions. By mining (attribute, value) pairs from the revision history of the English Wikipedia we are able to collect a comprehensive knowledge base that contains data on how attributes change over time. When dealing with the Wikipedia edit history, vandalic and erroneous edits are a concern for data quality. We present a study of vandalism identification in Wikipedia edits that uses only features from the infoboxes, and show that we can obtain, on this dataset, an accuracy comparable to a state-of-the-art vandalism identification method that is based on the whole article. Finally, we discuss different characteristics of the extracted dataset, which we make available for further study.

Information retrieval baselines for the ResPubliQA task

The baselines proposed for the ResPubliQA 2009 task are described in this paper. The main aim for designing these baselines was to test the performance of a pure Information Retrieval approach on this task. Two baselines were run for each of the eight languages of the task. Both baselines used the Okapi-BM25 ranking function, with and without a stemming. In this paper we extend the previous baselines comparing the BM25 model with Vector Space Model performance on this task. The results prove that BM25 outperforms VSM for all cases.

Approaching question answering by means of paragraph validation

In this paper we describe the QA system developed for taking part in Res-PubliQA 2009. Our system was composed by an IR phase focused on improving QA results, a validation step for removing paragraphs that are not promising and a module based on ngrams overlapping for selecting the final answer. Furthermore, a selection module that uses lexical entailment in combination with ngrams overlapping was developed in English. The IR module achieved very promising results that were improved by the ngram ranking. Moreover, the ranking was slightly improved when lexical entailment was used.

Answering questions about European legislation

ResPubliQA is a Question Answering (QA) evaluation task over European legislation whose first edition was proposed at the Cross Language Evaluation Forum (CLEF) 2009. The exercise consists of extracting a relevant paragraph of text that satisfies the information need expressed by a natural language question. The definition of the task allows to compare current QA technologies with pure Information Retrieval (IR) approaches and to introduce Answer Validation technologies in QA systems. In this paper we describe a system developed for this task. Our system is composed by an IR phase focused on improving QA results, a validation step for removing not promising paragraphs and a module based on n-grams overlapping for selecting the final answer, as well as a selection module that uses Lexical Entailment. While the IR module has contributed to obtain promising results, the performance of the validation module has to be improved. On the other hand, the n-gram ranking improved the results of the ranking given by the IR module.

On the high density of leadership nuclei in endorsement social networks

In this paper we study the community structure of <i>endorsement networks</i>, i.e., social networks in which a directed edge <i>u</i> → <i>v</i> is asserting an action of support from user <i>u</i> to user <i>v</i>. Examples include scenarios in which a user <i>u</i> is <i>favoring</i> a photo, <i>liking</i> a post, or <i>following</i> the microblog of user <i>v</i>. Starting from the hypothesis that the footprint of a community in an endorsement network is a bipartite directed clique from a set of followers to a set of leaders, we apply frequent itemset mining techniques to discover such bicliques. Our analysis of real networks discovers that an interesting phenomenon is taking place: the leaders of a community are endorsing each other forming a <i>very dense nucleus</i>.