Search Results for author: Amir Saffari

Found 9 papers, 3 papers with code

Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection

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.

Knowledge Graphs Question Answering

End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs

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.

Entity Resolution Knowledge Graphs +1

Relation Extraction from Tables using Artificially Generated Metadata

no code implementations24 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.

Relation Extraction

What do Models Learn from Question Answering Datasets?

1 code implementation 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.

Question Answering Reading Comprehension

Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs

no code implementations1 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).

Denoising Knowledge Graphs +1

Alternating Decision Forests

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.

object-detection Object Detection

Learning Anchor Planes for Classification

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.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.