Skip to search formSkip to main contentSkip to account menu

MolGAN: An implicit generative model for small molecular graphs

MolGAN is introduced, an implicit, likelihood-free generative model for small molecular graphs that circumvents the need for expensive graph matching procedures or node ordering heuris-tics of previous likelihood-based methods.
View PDF on arXiv (opens in a new tab)

Autoregressive Entity Retrieval

Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per article). The ability to retrieve such…
View PDF on arXiv (opens in a new tab)

Hyperspherical Variational Auto-Encoders

This work proposes using a von Mises-Fisher distribution instead of a Gaussian distribution for both the prior and posterior of the Variational Auto-Encoder, leading to a hyperspherical latent space.
View PDF on arXiv (opens in a new tab)

KILT: a Benchmark for Knowledge Intensive Language Tasks

It is found that a shared dense vector index coupled with a seq2seq model is a strong baseline, outperforming more tailor-made approaches for fact checking, open-domain question answering and dialogue, and yielding competitive results on entity linking and slot filling, by generating disambiguated text.
View on ACL (opens in a new tab)

Editing Factual Knowledge in Language Models

This work presents KnowledgeEditor, a method which can be used to edit factual knowledge and, thus, fix ‘bugs’ or unexpected predictions without the need for expensive re-training or fine-tuning.
View on ACL (opens in a new tab)

Question Answering by Reasoning Across Documents with Graph Convolutional Networks

A neural model which integrates and reasons relying on information spread within documents and across multiple documents is introduced, which achieves state-of-the-art results on a multi-document question answering dataset, WikiHop.
View on ACL (opens in a new tab)

Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking

This work introduces a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges and uses this technique as an attribution method to analyze GNN models for two tasks -- question answering and semantic role labeling -- providing insights into the information flow in these models.
View PDF on arXiv (opens in a new tab)

Block Neural Autoregressive Flow

Normalising flows (NFS) map two density functions via a differentiable bijection whose Jacobian determinant can be computed efficiently. Recently, as an alternative to hand-crafted bijections, Huang…
View PDF on arXiv (opens in a new tab)

Explorations in Homeomorphic Variational Auto-Encoding

The exper-iments show that choosing manifold-valued latent variables that match the topology of the latent data manifold, is crucial to preserve the topological structure and learn a well-behaved latent space.
View PDF on arXiv (opens in a new tab)

How Do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking

Differentiable Masking relies on learning sparse stochastic gates to completely mask-out subsets of the input while maintaining end-to-end differentiability and is used to study BERT models on sentiment classification and question answering.
View on ACL (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)