Most algorithms for representation learning and link prediction on relat...
Knowledge graphs (KGs) are inherently incomplete because of incomplete w...
The computation necessary for training Transformer-based language models...
Adapting pretrained language models to novel domains, such as clinical
a...
Knowledge graphs are powerful tools for representing and organising comp...
Explaining the decisions of neural models is crucial for ensuring their
...
State-of-the-art neural models can now reach human performance levels ac...
Answering complex queries on incomplete knowledge graphs is a challengin...
Background: Stratifying cancer patients according to risk of relapse can...
Access to external knowledge is essential for many natural language
proc...
Recently continuous relaxations have been proposed in order to learn Dir...
The integration of discrete algorithmic components in deep learning
arch...
Factorisation-based Models (FMs), such as DistMult, have enjoyed endurin...
Current Natural Language Inference (NLI) models achieve impressive resul...
In a task-oriented dialogue system, Dialogue State Tracking (DST) keeps ...
Relation Extraction in the biomedical domain is challenging due to the l...
Contemporary neural networks have achieved a series of developments and
...
We present NNMFAug, a probabilistic framework to perform data augmentati...
Learning good representations on multi-relational graphs is essential to...
Adaptive Computation (AC) has been shown to be effective in improving th...
Integrating discrete probability distributions and combinatorial optimiz...
Open-domain Question Answering models which directly leverage question-a...
Although reinforcement learning has been successfully applied in many do...
This paper proposes two intuitive metrics, skew and stereotype, that qua...
We review the EfficientQA competition from NeurIPS 2020. The competition...
Most approaches to Open-Domain Question Answering consist of a light-wei...
Neural link predictors are immensely useful for identifying missing edge...
The ability to quickly solve a wide range of real-world tasks requires a...
Attempts to render deep learning models interpretable, data-efficient, a...
Knowledge graph embeddings are now a widely adopted approach to knowledg...
Natural Language Inference (NLI) datasets contain annotation artefacts
r...
Current reading comprehension models generalise well to in-distribution ...
Reasoning with knowledge expressed in natural language and Knowledge Bas...
Rule-based models are attractive for various tasks because they inherent...
Recent advances in Neural Variational Inference allowed for a renaissanc...
Neural link predictors learn distributed representations of entities and...
Adversarial examples are inputs to machine learning models designed to c...
Neural models combining representation learning and reasoning in an
end-...
Many Machine Reading and Natural Language Understanding tasks require re...
We argue that extrapolation to examples outside the training space will ...
In adversarial training, a set of models learn together by pursuing comp...