19 citations · 72 across the 14 of their papers we have counts for
15 papers
When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
Elias Stengel-Eskin, Emmanouil Antonios Platanios, Adam Pauls +5
In natural language understanding (NLU) production systems, users' evolving needs necessitate the addition of new features over time, indexed by new symbols added to the meaning re…
Coarse-to-Fine Curriculum Learning
Otilia Stretcu, Emmanouil Antonios Platanios, Tom M. Mitchell +1
When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks…
Re-TACRED: Addressing Shortcomings of the TACRED Dataset
George Stoica, Emmanouil Antonios Platanios, Barnabás Póczos
TACRED is one of the largest and most widely used sentence-level relation extraction datasets. Proposed models that are evaluated using this dataset consistently set new state-of-t…
Constrained Language Models Yield Few-Shot Semantic Parsers
Richard Shin, Christopher H. Lin, Sam Thomson +7
We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural…
HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks
Zhou Xian, Shamit Lal, Hsiao-Yu Tung +2
We propose HyperDynamics, a dynamics meta-learning framework that conditions on an agent's interactions with the environment and optionally its visual observations, and generates t…
Improving Relation Extraction by Leveraging Knowledge Graph Link Prediction
George Stoica, Emmanouil Antonios Platanios, Barnabás Póczos
Relation extraction (RE) aims to predict a relation between a subject and an object in a sentence, while knowledge graph link prediction (KGLP) aims to predict a set of objects, O,…
Learning from Imperfect Annotations
Emmanouil Antonios Platanios, Maruan Al-Shedivat, Eric Xing +1
Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expens…
Jelly Bean World: A Testbed for Never-Ending Learning
Emmanouil Antonios Platanios, Abulhair Saparov, Tom Mitchell
Machine learning has shown growing success in recent years. However, current machine learning systems are highly specialized, trained for particular problems or domains, and typica…
Competence-based Curriculum Learning for Neural Machine Translation
Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig +2
Current state-of-the-art NMT systems use large neural networks that are not only slow to train, but also often require many heuristics and optimization tricks, such as specialized…
Contextual Parameter Generation for Universal Neural Machine Translation
Emmanouil Antonios Platanios, Mrinmaya Sachan, Graham Neubig +1
We propose a simple modification to existing neural machine translation (NMT) models that enables using a single universal model to translate between multiple languages while allow…
Agreement-based Learning
Emmanouil Antonios Platanios
Model selection is a problem that has occupied machine learning researchers for a long time. Recently, its importance has become evident through applications in deep learning. We p…
Deep Graphs
Emmanouil Antonios Platanios, Alex Smola
We propose an algorithm for deep learning on networks and graphs. It relies on the notion that many graph algorithms, such as PageRank, Weisfeiler-Lehman, or Message Passing can be…
Active Learning amidst Logical Knowledge
Emmanouil Antonios Platanios, Ashish Kapoor, Eric Horvitz
Structured prediction is ubiquitous in applications of machine learning such as knowledge extraction and natural language processing. Structure often can be formulated in terms of…
Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach
Emmanouil A. Platanios, Hoifung Poon, Tom M. Mitchell +1
We propose an efficient method to estimate the accuracy of classifiers using only unlabeled data. We consider a setting with multiple classification problems where the target class…
Mixture Gaussian Process Conditional Heteroscedasticity
Emmanouil A. Platanios, Sotirios P. Chatzis
Generalized autoregressive conditional heteroscedasticity (GARCH) models have long been considered as one of the most successful families of approaches for volatility modeling in f…