JU_KS_Group@FIRE 2016: Consumer Health Information Search

TL;DR

This paper presents a system for consumer health information search that classifies relevant sentences and their stance relative to a query, achieving competitive accuracy in the FIRE 2016 shared task.

Contribution

The paper introduces a methodology for classifying and determining the stance of sentences in consumer health documents, with competitive results in a shared evaluation.

Findings

Achieved 73.39% accuracy in classifying relevant sentences.

Ranked third among nine teams in the shared task.

Demonstrated effective stance classification in health information retrieval.

Abstract

In this paper, we describe the methodology used and the results obtained by us for completing the tasks given under the shared task on Consumer Health Information Search (CHIS) collocated with the Forum for Information Retrieval Evaluation (FIRE) 2016, ISI Kolkata. The shared task consists of two sub-tasks - (1) task1: given a query and a document/set of documents associated with that query, the task is to classify the sentences in the document as relevant to the query or not and (2) task 2: the relevant sentences need to be further classified as supporting the claim made in the query, or opposing the claim made in the query. We have participated in both the sub-tasks. The percentage accuracy obtained by our developed system for task1 was 73.39 which is third highest among the 9 teams participated in the shared task.