TY - JOUR
T1 - Graph-based approach to the Question Answering Task based on Entrance Exams
AU - Gómez-Adorno, Helena
AU - Sidorov, Grigori
AU - Pinto, David
AU - Gelbukh, Alexander
PY - 2014
Y1 - 2014
N2 - This paper describes the approach used in the system for the Question Answering Task based on Entrance Exams, which was presented at the CLEF 2014. The task aims to evaluate methods of text understanding with reading comprehension tests. The system should read a given document and answer multiple-choice questions about it. Our approach transforms the documents along with the multiple-choice answers into a graph-based representation that contains lexical, morphological, and syntactic features. After this, it traverses different paths both in the document itself and in the the graphs of the answers in order to find these features of the graphs. It is performed by counting text components: lemmas, PoS tags, grammatical tags. As the result of this procedure, the system constructs several feature vectors: one for each traversed graph. Finally, a cosine based similarity is calculated over these feature vectors in order to rank the multiple-choice answers and select the correct one-with the best similarity with the graph that corresponds to the text itself. Our system obtained a c@1 of 0.375, which was outperformed only by one system in the competition.
AB - This paper describes the approach used in the system for the Question Answering Task based on Entrance Exams, which was presented at the CLEF 2014. The task aims to evaluate methods of text understanding with reading comprehension tests. The system should read a given document and answer multiple-choice questions about it. Our approach transforms the documents along with the multiple-choice answers into a graph-based representation that contains lexical, morphological, and syntactic features. After this, it traverses different paths both in the document itself and in the the graphs of the answers in order to find these features of the graphs. It is performed by counting text components: lemmas, PoS tags, grammatical tags. As the result of this procedure, the system constructs several feature vectors: one for each traversed graph. Finally, a cosine based similarity is calculated over these feature vectors in order to rank the multiple-choice answers and select the correct one-with the best similarity with the graph that corresponds to the text itself. Our system obtained a c@1 of 0.375, which was outperformed only by one system in the competition.
KW - Entrance exams
KW - Extraction of features from graphs
KW - Graph similarity
KW - Graph-based representation
KW - Question answering system
KW - Reading comprehension
UR - http://www.scopus.com/inward/record.url?scp=84907510939&partnerID=8YFLogxK
M3 - Artículo de la conferencia
AN - SCOPUS:84907510939
SN - 1613-0073
VL - 1180
SP - 1395
EP - 1403
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
T2 - 2014 Cross Language Evaluation Forum Conference, CLEF 2014
Y2 - 15 September 2014 through 18 September 2014
ER -