Document Type

Conference Paper

Publication Date

2020

Publication Title

CEUR Workshop Proceedings: Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum

Volume

2696

Pages

121 (1-8)

Conference Name

CLEF 2020 - Conference and Labs of the Evaluation Forum, September 22-25, 2020, Thessaloniki, Greece

Abstract

This paper elaborates on our submission to the ARQMath track at CLEF 2020. Our primary run for the main Task-1: Question Answering uses a two-stage retrieval technique in which the first stage is a fusion of traditional BM25 scoring and tf-idf with cosine similarity-based retrieval while the second stage is a finer re-ranking technique using contextualized embeddings. For the re-ranking we use a pre-trained robertabase model (110 million parameters) to make the language model more math-aware. Our approach achieves a higher NDCG0 score than the baseline, while our MAP and P@10 scores are competitive, performing better than the best submission (MathDowsers) for text and text+formula dependent topics.

Comments

Link to conference landing page: https://ceur-ws.org/Vol-2696/

Rights

© 2020 of the authors.

Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) License.

Bibliographic data published under a Creative Commons CC0 1.0 Public Domain Dedication.

Original Publication Citation

Rohatgi, S., Wu, J., & Giles, C. L. (2020) PSU at CLEF-2020 ARQMath Track: Unsupervised re-ranking using pretraining. CEUR Workshop Proceedings, 2696, 121. https://ceur-ws.org/Vol-2696/paper_121.pdf

ORCID

0000-0003-0173-4463 (Wu)

Download

Share

COinS