Task 3a: Team YORKU

نویسندگان

  • Jiajin Wu
  • Xiangji Huang
چکیده

We used learning-to-rank methods for training ranking model. Due to the limited number of training queries, we split them and conducted 5-fold cross validation. We set the proportion of training and testing as 4 : 6. For the features used in learning the model, a total of 231 features that are from multiple information retrieval models with different parameter settings were adopted. For the baseline run, we used Random Forest method to train the models with 5-fold cross validation. Only the binary relevance information were taken into account while training the model. Five trained models from 5-fold cross validation were used on the testing data to predict scores, and then we used equal weights to linearly combine the results given by different models. For run #5, we used 8 learning to rank methods to train models separately and linearly combine them together, and the binary relevance judgment was used as well. For run #6 and #7, graded relevance were taken into consideration. The difference between run 6# and #7 is that for run #6, multiple learning-to-rank methods were used while for run #7, only Random Forest method was used. The best result of the four runs is achieved by run #5, which used multiple models combination based on binary relevance judgment.

برای دانلود رایگان 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

The Fudan Participation in the 2015 BioASQ Challenge: Large-scale Biomedical Semantic Indexing and Question Answering

This article describes the participation of Fudan team in the 2015 BioASQ challenge. The challenge consists of two tasks, largescale biomedical semantic indexing (task 3a) and biomedical question answering (task 3b). In task 3a, our method, MeSHLabeler, achieved the first place in all 15 weeks of three batches. Based on 3215 annotated citations (June 6, 2015) out of all 4435 citations in the of...

متن کامل

Effect of different seasonal strength training protocols on circulating androgen levels and performance parameters in professional soccer players.

OBJECTIVE To examine the effects of three seasonal training programs, largely different in strength volume, on androgen levels and performance parameters in soccer players. DESIGN Sixty-seven soccer players, members of three different professional teams, participated in the study. Strength intensity of the training programs were assessed as high (for Team-A, n=23), moderate (for Team-B, n=22)...

متن کامل

Comparison of the senior student with junior student's viewpoint about team working in Kurdistan University of medical sciences

Background: In regard to enhancement of efficiency and productivity of an organization in terms of teamwork, it is necessary to shift to team-centered approach for increasing confidence in health care systems. Therefore it is needed to assess effect of the academic training on students' viewpoint in team working. Methods: This was a cross-sectional study and was done in Kurdistan University of ...

متن کامل

AUTH-Atypon at BioASQ 3: Large-Scale Semantic Indexing in Biomedicine

In this paper we present the methods and the approaches employed in terms of our participation to the BioASQ Challenge 2015 and more specifically in task 3a, concerning the automatic semantic annotation of scientific abstracts. Based on the successful approaches of the previous years we considered a variety of ensembles, incorporated journalspecific semantic information and developed an approac...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014