WHU at TREC Total Recall Track 2015
نویسندگان
چکیده
This paper describes the WHU IRLAB participation to the Total Recall Track in TREC 2015. We implement an end-to-end system to deal with the total recall task. We propose an iterative query expansion method, which construct queries using iteratively selected terms. We choose to participate the "Play-at-home" evaluation. Results are presented and discussed.
منابع مشابه
WaterlooClarke: TREC 2015 Total Recall Track
The total recall track in TREC 2015 seeks an enhanced model to accelerate the autonomous technology-assisted review process. This paper introduces several noval ideas such as clustering based seed selection method, extended n-grams features and continuous query expansion learned from the relevant documents derived from each iteration. These methods can retrieve more relevant documents from each...
متن کاملWHU at TREC KBA Vital Filtering Track 2014
This paper describes the WHU IRLAB participation to the Vital Filtering task of the TREC 2014 Knowledge Base Acceleration Track. In this task, we implemented a system to detect vital documents that could be used for a human editor to update or create the profile of an entity. Our approach is to view the problem as a classification problem and use Stanford NLP Toolkit to extract necessary inform...
متن کاملTUW at the First Total Recall Track
Abstract. For the first participation in the TREC Total Recall track, we set out to try some basic changes to the baseline provided by the organisers. Namely, the weighting scheme, the use of stopwords, and the number of learners that contribute to the decision of which documents to ask the virtual assessor to review. We observed that the baseline was extremely strong and none of the runs signi...
متن کاملThe University of Amsterdam (ILPS) at TREC 2015 Total Recall Track
We describe the participation of the University of Amsterdams ILPS group in the Total Recall track at TREC 2015. Based on the provided Baseline Model Implemention (”BMI”) we set out to provide two more baselines we can compare to in future work. The two methods are bootstrapped by a synthetic document based on the query, use TF/IDF features, and sample with dynamic batch sizes which depend on t...
متن کاملWebis at TREC 2015: Tasks and Total Recall Tracks
In this paper we give a brief overview of the Webis group’s participation in the TREC 2015 Tasks and Total Recall tracks. In the task understanding subtask of the Tasks track, we use di erent data sources (AOL query log, Freebase, etc.) and APIs (Google, Bing, etc.) to retrieve topics related to a given query. All sources are combined in our SQuare system. The task completion subtask is based o...
متن کامل