A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
PACRR Gated Expansion for TREC CAR 2018
2018
Text Retrieval Conference
Preserved Fulltext
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]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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
2018
The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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