Graph-Based Answer Fusion in Multilingual Question Answering
نویسندگان
چکیده
One major problem in multilingual Question Answering (QA) is the combination of answers obtained from different languages into one single ranked list. This paper proposes a new method for tackling this problem. This method is founded on a graph-based ranking approach inspired in the popular Google’s PageRank algorithm. Experimental results demonstrate that the proposed method outperforms other current techniques for answer fusion, and also evidence the advantages of multilingual QA over the traditional monolingual approach.
منابع مشابه
Fusión de Respuestas en la Búsqueda de Respuestas Multilinge
This paper describes the main challenges of multilingual question answering. In particular, it focuses on the problem of answer fusion, which concerns the combination of answers obtained from collections in different languages. Basically, it compares a set of techniques for answer fusion, previously used in other multilingual tasks, in the problem of multilingual question answering. On the basi...
متن کاملMultilingual Question/Answering: the DIOGENE System
This paper presents the DIOGENE question/answering system developed at ITCIrst. The system is based on a rather standard architecture which includes three components for question processing, search and answer extraction. Linguistic processing strongly relies on MULTIWORDNET, an extended version of the English WORDNET. The system has been designed to address two promising directions: multilingua...
متن کاملText-to-text generation for question answering
When answering questions, major challenges are (a) to carefully determine the content of the answer and (b) phrase it in a proper way. In IMIX, we focus on two text-to-text generation techniques to accomplish this: content selection and sentence fusion. Using content selection, we can extend answers to an arbitrary length, providing not just a direct answer but also related information so to be...
متن کاملUsing Information Fusion for Open Domain Question Answering
In open domain Question Answering, answer candidates are ranked according to individual features such as matching the answer type expected by the question. We report on a technique based on the fusion of candidate answers and their context into answer neighbourhoods to provide better features for ranking and allow shallow reasoning.
متن کاملMultilingual Pattern Libraries for Question Answering: a Case Study for Definition Questions
In this paper we investigate the effectiveness of a novel resource for Multilingual Question Answering (QA). Such a resource consists of a set of multilingual pattern libraries for answer extraction and validation. In the spirit of the ongoing attempts to develop freely available resources for QA, we argue that the distribution and use of pattern libraries will contribute to make Multilingual Q...
متن کامل