Dallas Fraser, Andrew Kane and Frank Tompa win best paper award at DocEng 2018

Wednesday, September 12, 2018

Recent computer science PhD graduate and postdoctoral fellow Andrew Kane, MMath graduate Dallas Fraser, and Distinguished Professor Emeritus Frank Tompa have received the best paper award at DocEng 2018, the 18th ACM Symposium on Document Engineering.

photo of Andrew Kane,  Dallas Fraser, Distinguished Professor Emeritus Frank Tompa

L to R: Postdoctoral fellow Andrew Kane, MMath graduate Dallas Fraser, and Distinguished Professor Emeritus Frank Tompa

Their paper, titled Choosing Math Features for BM25 Ranking with Tangent-L, explores how to adapt the state-of-the-art BM25 text ranking method to work effectively when searching for mathematical symbols with text in documents. The research was presented at DocEng’s annual symposium held this year in Halifax, Nova Scotia from August 28–31, 2018.

“Congratulations to Dallas, Andrew and Frank for receiving the prestigious best paper award at DocEng 2018,” said Dan Brown, Director of the David R. Cheriton School of Computer Science.

“Their work is of great importance because mathematical formulae are sprinkled throughout a wide range of documents, spanning fields from astronomy to economics to zoology. Searching through documents that have extensive mathematical formulae and symbols remains an open problem, but Dallas and his colleagues have shown that a traditional search engine and ranking chosen for particular math features performs comparably or better than the state-of-the art math retrieval system.”


To learn more about this research, please see Dallas Fraser, Andrew Kane and Frank Wm. Tompa. 2018. Choosing Math Features for BM25 Ranking with Tangent-L. In DocEng ’18: ACM Symposium on Document Engineering 2018, August 28–31, 2018, Halifax, NS. Canada. ACM, New York, NY, USA.

  1. 2024 (5)
    1. October (1)
    2. September (1)
    3. August (1)
    4. June (1)
    5. March (1)
  2. 2023 (4)
    1. November (1)
    2. May (1)
    3. January (2)
  3. 2022 (4)
    1. December (1)
    2. November (1)
    3. October (1)
    4. June (1)
  4. 2021 (5)
  5. 2020 (9)
  6. 2019 (3)
  7. 2018 (16)
  8. 2017 (11)
  9. 2016 (2)