342 citations · 472 across the 8 of their papers we have counts for
8 papers
Are Deep Sequence Classifiers Good at Non-Trivial Generalization?
Francesco Cazzaro, Ariadna Quattoni, Xavier Carreras
Recent advances in deep learning models for sequence classification have greatly improved their classification accuracy, specially when large training sets are available. However,…
Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing
Francesco Cazzaro, Davide Locatelli, Ariadna Quattoni +1
Prior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks. This limitation led to a resurgence of methods that model alig…
Arc-Standard Spinal Parsing with Stack-LSTMs
Miguel Ballesteros, Xavier Carreras
We present a neural transition-based parser for spinal trees, a dependency representation of constituent trees. The parser uses Stack-LSTMs that compose constituent nodes with depe…
A Maximum Matching Algorithm for Basis Selection in Spectral Learning
Ariadna Quattoni, Xavier Carreras, Matthias Gallé
We present a solution to scale spectral algorithms for learning sequence functions. We are interested in the case where these functions are sparse (that is, for most sequences they…
Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison
Pranava Swaroop Madhyastha, Xavier Carreras, Ariadna Quattoni
We investigate the problem of inducing word embeddings that are tailored for a particular bilexical relation. Our learning algorithm takes an existing lexical vector space and comp…
Local Loss Optimization in Operator Models: A New Insight into Spectral Learning
Borja Balle, Ariadna Quattoni, Xavier Carreras
This paper re-visits the spectral method for learning latent variable models defined in terms of observable operators. We give a new perspective on the method, showing that operato…