Reading Comprehension at Entrance Exams 2015

نویسندگان

  • Dominique Laurent
  • Baptiste Chardon
  • Sophie Nègre
  • Camille Pradel
  • Patrick Séguéla
چکیده

This article presents the participation of Synapse Développement to the CLEF 2015 Entrance Exam campaign (QA track) for English and French languages. Since fifteen years, our company works on Question Answering domain. Recently our work concentrated on Machine Reading and Natural Language understanding. Thus, the Entrance Exam evaluation is an excellent opportunity to measure the results of this work. The developed system is based on a deep syntactic and semantic analysis with anaphora resolution and some inference mechanisms. The results of this analysis are saved in sophisticated structures based on clause description (CDS = Clause Description Structure). For this evaluation, we added a dedicated module to compare CDS from texts, questions and answers. This module measures the degree of correspondence between these elements, taking into account the type of answer awaited. We participated in English and French languages. This run obtains the best results (52 good answers on 89 in English and 50 on 89 in French). So, in English and French, our system can pass the entrance exam for University!

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Overview of CLEF QA Entrance Exams Task 2015

This paper describes the Entrance Exams task at the CLEF QA Track 2015. Following the last two editions, the data set has been extracted from actual university entrance examinations including a variety of topics and question types. Systems receive a set of Multiple-Choice Reading Comprehension tests where the task is to select the correct answer among a finite set of candidates, according to th...

متن کامل

CoMiC: Exploring Text Segmentation and Similarity in the English Entrance Exams Task

This paper describes our contribution to the English Entrance Exams task of CLEF 2015, which requires participating systems to automatically solve multiple choice reading comprehension tasks. We use a combination of text segmentation and different similarity measures with the aim of exploiting two observed aspects of tests: 1) the often linear relationship between reading text and test question...

متن کامل

Overview of CLEF QA Entrance Exams Task 2014

This paper describes the Entrance Exams task at the CLEF QA Track 2014. Following 2013 edition, the data set has been extracted from actual university entrance examinations including a variety of topics and question types. Systems receive a set of Multiple-Choice Reading Comprehension tests where the task is to select the correct answer among a finite set of candidates, according to the given t...

متن کامل

Overview 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

Improving Iranian EFL students reading comprehension skills: examining the effects of self-regulated strategy and modified reciprocal teaching

The purpose of this study was to investigate how reciprocal teaching and self-regulation affected reading comprehension of EFL learners at the high school level. 60 participants were selected and randomly assigned into two groups: an experimental group and a control group. The experimental group was taught through reciprocal teaching while the control group was taught through skill-based teachi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015