Testing Lexical Approaches in QA4MRE
نویسندگان
چکیده
In this paper we describe our strategy in the course of our participation in the 2012 QA4MRE main task. We follow a lexical approach, based on both Word Proximity and similarity measures. In the former, we implement a method that was successfully applied in the “Who Wants to be a Millionaire” contest; in the later we use the notion of “extent”, that is, a passage that includes terms of the given questions or answers, and results from comparing the attained extents through widely known similarity measures such as Jaccard and Dice. Considering the 2011 QA4MRE competition, our results are promising, although still far from the ones attained by the winning system.
منابع مشابه
Two Approaches for QA4MRE: Information Retrieval and Graph-based Knowledge Representation
In this paper we present our approaches for tackling the QA4MRE 2013 main task. We have built two different methodologies, one based on information retrieval and the other one based on graph representations of the text, additionally we have built a third hybrid methodology combining both of the previous one. The first methodology uses the Lucene information retrieval engine for carrying out inf...
متن کاملQuestion Answering for Machine Reading with Lexical Chain
Question answering for machine reading (QA4MR) is a task to understand the meaning communicated by a text. In this paper, we present our system in QA4MRE. The system follows the steps of reading comprehension as a language learner. Lexical chain is used to estimate the semantic relation between texts. Natural language processing (NLP) techniques are also widely used, such as: POS tagging, name ...
متن کاملSelecting Answers with Structured Lexical Expansion and Discourse Relations LIMSI's Participation at QA4MRE 2013
In this paper, we present the LIMSI’s participation to QA4MRE 2013.We decided to test two kinds of methods. The first one focuses on complex questions, such as causal questions, and exploits discourse relations. Relation recognition shows promising results, however it has to be improved to have an impact on answer selection. The second method is based on semantic variations. We explored the Eng...
متن کاملCombining Text Mining Techniques for QA4MRE 2013
This paper describes a lexical system developed for the main task of Question Answering for Machine Reading Evaluation 2013 (QA4MRE). The presented system executes the preprocessing of test documents, and generates hypotheses consisting of the question text combined with text from possible answers for the question. The hypotheses are compared to sentences from the text by the means of a set sim...
متن کاملOverview of QA4MRE 2013 Entrance Exams Task
This paper describes the Question Answering for Machine Reading (QA4MRE) Entrance Exams at the 2013 Cross Language Evaluation Forum. The data set of this task is extracted from actual university entrance examinations as-is, and therefore includes a variety of topics in daily life. Another unique feature of the Entrance Exams task is that questions are designed originally for testing human exami...
متن کامل