WaterlooClarke: TREC 2015 Total Recall Track
نویسندگان
چکیده
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 iteration thereby achieving high recall while requiring less review e↵ort.
منابع مشابه
WaterlooClarke: TREC 2015 Contextual Suggestion Track
In this work we present a first attempt at developing a live system to solve the problem presented in the TREC 2015 contextual suggestion task. The goal of this task is to tailor point-of-interest suggestions to users according to their preferences [3]. We present how we gathered data for the candidate pointsof-interest, filtered some of the candidates and built a live system to return suggesti...
متن کاملWaterlooClarke: TREC 2015 Microblog Track
The goal of the TREC 2015 Microblog Track is to develop a real-time relevancy retrieval system that monitors a stream of social media posts and recommends relevant posts according to users’ interests [1]. In this track, the representative social media is Twitter, and relevant posts are tweets with respect to a user’s interest. A user’s interest is represented by an interest profile containing a...
متن کاملWaterlooClarke: TREC 2015 LiveQA Track
The goal of the LiveQA track is to automatically provide answers to questions posted by real people. Previous question answering tracks included factoid questions, list questions and complex questions[3]. Presented in 2015 for the first time the LiveQA track gave the participants an opportunity to answer questions posed by real people, as opposed to manually configured ones in the previous task...
متن کاملWHU at TREC Total Recall Track 2015
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.
متن کاملWaterlooClarke: TREC 2015 Clinical Decision Support Track
Clinical decision support systems help physicians with finding additional information about a particular medical case. In this paper, we develop a clinical decision support system that, based on a short medical case description, can recommend research articles to answer some common medical questions (diagnosis, test and treatment articles). The two different full-text search engines we adopted ...
متن کاملذخیره 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 2015