Neural retrievers have been shown to be effective for math-aware search. Their ability to cope with math symbol mismatches, to represent highly contextualized semantics, and to …
V Novotný, M Stefánik - CLEF (Working Notes), 2022 - ceur-ws.org
Sparse retrieval techniques can detect exact matches, but are inadequate for mathematical texts, where the same information can be expressed as either text or math. The soft vector …
Q Liu, W Guan, J Shen, F Cheng… - arXiv preprint arXiv …, 2022 - arxiv.org
Previous studies have introduced a weakly-supervised paradigm for solving math word problems requiring only the answer value annotation. While these methods search for …
One of the challenges of math information retrieval is the inherent ambiguity of mathematical notation. The use of various notations, symbols, and conventions can lead to ambiguities in …
W Zhong, Y Xie, J Lin - International Conference of the Cross-Language …, 2023 - Springer
Answer retrieval for math questions is a challenging task due to the complex and structured nature of mathematical expressions. In this paper, we combine a structure retriever and a …
B Mansouri, S Durgin, SJ Franklin, S Fletcher… - CLEF (Working …, 2023 - sheadurgin.com
This paper describes the participation of the Artificial Intelligence and Information Retrieval (AIIR) Lab from the University of Southern Maine and the Laboratory of Artificial Intelligence …
Numerical reasoning plays a pivotal role in both the realm of natural language processing (NLP) research and real-life applications. Numerical reasoning, as an integral component of …
The ever-increasing volume of web-based documents poses a challenge in efficiently accessing specialized knowledge from domain-specific sources, requiring a profound …