paper-with-me

홈 › Papers

To be or not to be an Integer? Encoding Variables for Mathematical Text

2022-05-01 · Findings (ACL) 2022 5 · Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, Julia Rozanova, Andre Freitas

The application of Natural Language Inference (NLI) methods over large textual corpora can facilitate scientific discovery, reducing the gap between current research and the available large-scale scientific knowledge. However, contemporary NLI models are still limited in interpreting mathematical knowledge written in Natural Language, even though mathematics is an integral part of scientific argumentation for many disciplines. One of the fundamental requirements towards mathematical language understanding, is the creation of models able to meaningfully represent variables. This problem is particularly challenging since the meaning of a variable should be assigned exclusively from its defining type, i.e., the representation of a variable should come from its context. Recent research has formalised the variable typing task, a benchmark for the understanding of abstract mathematical types and variables in a sentence. In this work, we propose VarSlot, a Variable Slot-based approach, which not only delivers state-of-the-art results in the task of variable typing, but is also able to create context-based representations for variables.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Inferencescientific discoverySentence

Similar Papers 제목 키워드 기반

Mixed-Integer Programming for Signal Temporal Logic with Fewer Binary Variables

2022-04-13 · Vince Kurtz, Hai Lin

Signal Temporal Logic (STL) provides a convenient way of encoding complex control objectives for robotic and cyber-physical systems. The state-of-the-art in trajectory synthesis for STL is based on Mixed-Integer Convex P…

Faster Certified Symmetry Breaking Using Orders With Auxiliary Variables

2025-11-20 · Markus Anders, Bart Bogaerts, Benjamin Bogø, Arthur Gontier 외 arxiv

Symmetry breaking is a crucial technique in modern combinatorial solving, but it is difficult to be sure it is implemented correctly. The most successful approach to deal with bugs is to make solvers certifying, so that …

Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features

2021-04-01 · Florian Pargent, Florian Pfisterer, Janek Thomas, Bernd Bischl

Since most machine learning (ML) algorithms are designed for numerical inputs, efficiently encoding categorical variables is a crucial aspect in data analysis. A common problem are high cardinality features, i.e. unorder…

BIG-bench Machine Learning

Dealing with Categorical and Integer-valued Variables in Bayesian Optimization with Gaussian Processes

2018-05-09 · Eduardo C. Garrido-Merchán, Daniel Hernández-Lobato

Bayesian Optimization (BO) methods are useful for optimizing functions that are expen- sive to evaluate, lack an analytical expression and whose evaluations can be contaminated by noise. These methods rely on a probabili…

Bayesian OptimizationGaussian Processes

Black-box optimization for integer-variable problems using Ising machines and factorization machines

2022-09-01 · Yuya Seki, Ryo Tamura, Shu Tanaka

Black-box optimization has potential in numerous applications such as hyperparameter optimization in machine learning and optimization in design of experiments. Ising machines are useful for binary optimization problems …

Hyperparameter Optimization