no code implementations • 7 Jun 2023 • Jinheon Baek, Alham Fikri Aji, Amir Saffari
We validate the performance of our KAPING framework on the knowledge graph question answering task, that aims to answer the user's question based on facts over a knowledge graph, on which ours outperforms relevant zero-shot baselines by up to 48% in average, across multiple LLMs of various sizes.
no code implementations • 13 Oct 2022 • Andy Rosenbaum, Saleh Soltan, Wael Hamza, Amir Saffari, Marco Damonte, Isabel Groves
A bottleneck to developing Semantic Parsing (SP) models is the need for a large volume of human-labeled training data.
1 code implementation • COLING 2022 • Priyanka Sen, Alham Fikri Aji, Amir Saffari
We introduce Mintaka, a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models.
no code implementations • EMNLP 2021 • Armin Oliya, Amir Saffari, Priyanka Sen, Tom Ayoola
Our model only needs the question text and the answer entities to train, and delivers a stand-alone QA model that does not require an additional ER component to be supplied during runtime.
1 code implementation • EMNLP 2021 • Priyanka Sen, Amir Saffari, Armin Oliya
End-to-end question answering using a differentiable knowledge graph is a promising technique that requires only weak supervision, produces interpretable results, and is fully differentiable.
no code implementations • 24 Aug 2021 • Gaurav Singh, Siffi Singh, Joshua Wong, Amir Saffari
To address this issue, we propose methods to artificially create some of this metadata for synthetic tables.
1 code implementation • COLING 2020 • Hamza Harkous, Isabel Groves, Amir Saffari
Our generated text has a significantly better semantic fidelity than the state of the art across all four datasets
Ranked #1 on Data-to-Text Generation on ViGGO
2 code implementations • EMNLP 2020 • Priyanka Sen, Amir Saffari
While models have reached superhuman performance on popular question answering (QA) datasets such as SQuAD, they have yet to outperform humans on the task of question answering itself.
no code implementations • 1 Dec 2018 • Daniel Neil, Joss Briody, Alix Lacoste, Aaron Sim, Paidi Creed, Amir Saffari
In this work, we provide a new formulation for Graph Convolutional Neural Networks (GCNNs) for link prediction on graph data that addresses common challenges for biomedical knowledge graphs (KGs).
no code implementations • ICLR 2019 • Rim Assouel, Mohamed Ahmed, Marwin H Segler, Amir Saffari, Yoshua Bengio
Generating novel molecules with optimal properties is a crucial step in many industries such as drug discovery.
no code implementations • CVPR 2013 • Samuel Schulter, Paul Wohlhart, Christian Leistner, Amir Saffari, Peter M. Roth, Horst Bischof
Contrary to Boosted Trees, in our method the loss minimization is an inherent part of the tree growing process, thus allowing to keep the benefits of common Random Forests, such as, parallel processing.
no code implementations • NeurIPS 2011 • Ziming Zhang, Lubor Ladicky, Philip Torr, Amir Saffari
It provides a set of anchor points which form a local coordinate system, such that each data point on the manifold can be approximated by a linear combination of its anchor points, and the linear weights become the local coordinate coding.