Filters








4 Hits in 2.5 sec

PACRR Gated Expansion for TREC CAR 2018

Sean MacAvaney, Nazli Goharian, Ophir Frieder, Andrew Yates
2018 Text Retrieval Conference  
The second run incorporates a novel gated technique for incorporating query expansion terms in a neural ranker.  ...  In this work, we present our approach to the 2018 TREC Complex Answer Retrieval (CAR) task. We submitted two passage retrieval runs.  ...  For our guir-exp run, we use the top 100 expansion terms from Relevance Model 3 [4] , and set k exp = 10. Our results for TREC CAR 2018 are given in Table 1 .  ... 
dblp:conf/trec/MacAvaneyGFY18 fatcat:3o7hjlidg5aqbcjfljxayw7s5u

Characterizing Question Facets for Complex Answer Retrieval [article]

Sean MacAvaney, Andrew Yates, Arman Cohan, Luca Soldaini, Kai Hui, Nazli Goharian, Ophir Frieder
2018 arXiv   pre-print
When we use our techniques with a leading neural ranker on the TREC CAR dataset, our methods rank first in the 2017 TREC CAR benchmark, and yield up to 26% higher performance than the next best method.  ...  In this work, we present two novel approaches for CAR based on the observation that question facets can vary in utility: from structural (facets that can apply to many similar topics, such as 'History'  ...  [8] presents a survey of prominent general domain ranking and query expansion approaches for CAR.  ... 
arXiv:1805.00791v1 fatcat:gl5et3bb4zhrppgo73dgiaz45i

Characterizing Question Facets for Complex Answer Retrieval

Sean MacAvaney, Andrew Yates, Arman Cohan, Luca Soldaini, Kai Hui, Nazli Goharian, Ophir Frieder
2018 The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18  
When we use our techniques with a leading neural ranker on the TREC CAR dataset, our methods rank first in the 2017 TREC CAR benchmark, and yield up to 26% higher performance than the next best method.  ...  In this work, we present two novel approaches for CAR based on the observation that question facets can vary in utility: from structural (facets that can apply to many similar topics, such as 'History'  ...  [8] presents a survey of prominent general domain ranking and query expansion approaches for CAR.  ... 
doi:10.1145/3209978.3210135 dblp:conf/sigir/MacAvaneyYCSHGF18 fatcat:iaiwchafyjbqhbhfh7vtb2dgye

Learning Representations and Agents for Information Retrieval [article]

Rodrigo Nogueira
2019 arXiv   pre-print
This progress can be partially attributed to the recent success of machine learning and to the efficient methods for storing and retrieving information, most notably through web search engines.  ...  We argue, however, that although this approach has been very successful for tasks such as machine translation, storing the world's knowledge as parameters of a learning machine can be very hard.  ...  functions on TREC-CAR.  ... 
arXiv:1908.06132v1 fatcat:xcujtsvsd5clljkteu4zrmr4hy