no code implementations • EMNLP 2021 • Johanna Björklund, Adam Dahlgren Lindström, Frank Drewes
There is a growing consensus that surface form alone does not enable models to learn meaning and gain language understanding.
no code implementations • 19 Apr 2023 • Andrea Aler Tubella, Dimitri Coelho Mollo, Adam Dahlgren Lindström, Hannah Devinney, Virginia Dignum, Petter Ericson, Anna Jonsson, Timotheus Kampik, Tom Lenaerts, Julian Alfredo Mendez, Juan Carlos Nieves
Fairness is central to the ethical and responsible development and use of AI systems, with a large number of frameworks and formal notions of algorithmic fairness being available.
1 code implementation • 10 Aug 2022 • Adam Dahlgren Lindström, Savitha Sam Abraham
We introduce CLEVR-Math, a multi-modal math word problems dataset consisting of simple math word problems involving addition/subtraction, represented partly by a textual description and partly by an image illustrating the scenario.
no code implementations • 6 Apr 2022 • Johanna Björklund, Adam Dahlgren Lindström, Frank Drewes
The objective is to simultaneously fill in the missing algebraic operations in $\alg$ and ground the variables of every $\varphi_i$ in $O_i$, so that the combined value of the terms is optimised.
1 code implementation • COLING 2020 • Adam Dahlgren Lindström, Suna Bensch, Johanna Björklund, Frank Drewes
Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed.