Fernando Llopis

Question Answering in Spanish

This paper describes the architecture, operation and results obtained with the Question Answering prototype for Spanish developed in the Department of Language Processing and Information Systems at the University of Alicante for the CLEF 2003 Spanish monolingual QA evaluation task. Our system has been fully developed from scratch and it combines shallow natural language processing tools with statistical data redundancy techniques. The system is able to perform QA tasks independently from static corpora or from Web documents. Moreover, the World Wide Web can be used as an external resource to obtain evidence to support and complement the CLEF Spanish corpora.

AliQAn, spanish QA system at CLEF-2005

Question Answering is a major research topic at the University of Alicante. For this reason, this year two groups participated in the QA@CLEF track using different approaches. In this paper we describe the work of Alicante 2 group. This paper describes AliQAn, a monolingual open-domain Question Answering (QA) System developed in the Department of Language Processing and Information Systems at the University of Alicante for CLEF-2005 Spanish monolingual QA evaluation task. Our approach is based fundamentally on the use of syntactic pattern recognition in order to identify possible answers. Besides this, Word Sense Disambiguation (WSD) is applied to improve the system. The results achieved (overall accuracy of 33%) are shown and discussed in the paper.

Passage selection to improve Question Answering

Open-Domain Question Answering systems (QA) performs the task of detecting text fragments in a collection of documents that contain the response to users queries. These systems use high complexity tools that reduce its applicability to the treatment of small amounts of text. Consequently, when working on large document collections, QA systems apply Information Retrieval (IR) techniques to reduce drastically text collections to a tractable quantity of relevant text. In this paper, we propose a novel Passage Retrieval (PR) model that performs this task with better performance for QA purposes than current best IR systems

IR-n: A Passage Retrieval System at CLEF-2001

Previous work demonstrates that information retrieval system performance is sensibly improved when using document passages as the basic unit of information. However, the IR community has not yet arrived at consensus about the best way of defining text passages for retrieval purposes. This paper reports on experiments with the IR-n system, an information retrieval system that applies a new method for passage selection. Passages are defined as a fixed number of adjoining sentences in a document. This approach has been tested for the monolingual (Spanish) and bilingual (Spanish-English) tasks at CLEF-2001 with different success rates.

Improving question answering using named entity recognition

This paper studies the use of Named Entity Recognition (NER) for the Question Anwering (QA) task in Spanish texts. NER applied as a preprocessing step not only helps to detect the answer to the question but also decreases the amount of data to be considered by QA. Our proposal reduces a 26% the quantity of data and moreover increases a 9% the efficiency of the system.

IR-n System at CLEF-2002

Passage Retrieval is an alternative to traditional document-oriented Information Retrieval. These systems use contiguous text fragments (or passages) instead of full documents as the basic unit of information. The IR-n system is a passage retrieval system that uses groups of contiguous sentences as units of information. This paper reports on experiments with the IR-n system at CLEF-2002 where it has obtained considerably better results than in the previous participation in CLEF-2001.

Reducing question answering input data using named entity recognition

In a previous paper we proved that Named Entity Recognition plays an important role to improve Question Answering by both increasing the quality of the data and by reducing its quantity. Here we present a more in-depth discussion, studying several ways in which NER can be applied in order to produce a maximum data reduction. We achieve a 60% reduction without significant data loss and a 92.5% with a reasonable implication in data quality.

Text Segmentation for Efficient Information Retrieval

Previous works in Information Retrieval show that using pieces of text obtain better results than using the whole document as the basic unit to compare with the users query. This kind of IR systems is usually called Passage Retrieval (PR). However, there is not a general agreement about how one should define those pieces of text (also known as passages), in order to obtain an optimum performance. This paper proposes a PR system based on a novel selection of variable size passages. It presents an evaluation that shows better results than a standard IR system and several well-known PR systems.

Monolingual and cross-lingual QA using AliQAn and BRILI systems for CLEF 2006

A previous version of AliQAn participated in the CLEF 2005 Spanish Monolingual Question Answering task. For this years run, to the system are added new and representative patterns in question analysis and extraction of the answer. A new ontology of question types has been included. The inexact questions have been improved. The information retrieval engine has been modified considering only the detected keywords from the question analysis module. Besides, many PoS Tagger and SUPAR errors have been solved and finally, dictionaries about cities and countries have been incorporated. To deal with Cross-Lingual tasks, we employ the BRILI system. The achieved results are overall accuracy of 37.89% for monolingual and 21.58% for bilingual tasks.

Does english help question answering in spanish

This paper describes the architecture, operation and results obtained with the Question Answering prototype for Spanish developed in the Department of Language Processing and Information Systems at the University of Alicante for the CLEF-2004 Spanish monolingual QA evaluation task. Our system is based on the prototype developed for the CLEF-2003 Spanish monolingual task [3]. This system has been enhanced with capabilities regarding the use of documents in different languages to obtain evidence for supporting and complementing the CLEF Spanish corpora. In particular, the experiments described are intended to study how to use English Web documents to support monolingual Spanish QA.