no code implementations • 5 Mar 2024 • Savitha Sam Abraham, Marjan Alirezaie, Luc De Raedt
In CLEVR-POC, knowledge in the form of logical constraints needs to be leveraged to generate plausible answers to questions about a hidden object in a given partial scene.
1 code implementation • 21 Jan 2023 • Anoop Kadan, Deepak P., Manjary P. Gangan, Savitha Sam Abraham, Lajish V. L
Towards this, we leverage context-specific and affect enriched representations by using a transformer-based pre-trained language model in tandem with affect enriched Bi-LSTM+Attention.
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 • 31 May 2022 • Sowmya S Sundaram, Sairam Gurajada, Marco Fisichella, Deepak P, Savitha Sam Abraham
From the latter half of the last decade, there has been a growing interest in developing algorithms for automatically solving mathematical word problems (MWP).
no code implementations • AAAI Workshop CLeaR 2022 • Savitha Sam Abraham, Marjan Alirezaie
Compositional generalization is the ability to understand novel combinations of known concepts.
no code implementations • 11 Oct 2020 • Deepak P, Savitha Sam Abraham
We illustrate the importance of representativity fairness in real-world decision making scenarios involving clustering and provide ways of quantifying objects' representativity and fairness over it.
no code implementations • 20 May 2020 • Deepak P, Savitha Sam Abraham
Being a novel task, we develop an evaluation framework for fair outlier detection, and use that to benchmark FairLOF on quality and fairness of results.
no code implementations • 11 Oct 2019 • Savitha Sam Abraham, Deepak P, Sowmya S Sundaram
Our experimental evaluation illustrates that the clusters generated by FairKM fare significantly better on both clustering quality and fair representation of sensitive attribute groups compared to the clusters from a state-of-the-art baseline fair clustering method.