no code implementations • Findings (EMNLP) 2021 • Ariadna Quattoni, Xavier Carreras
We address the annotation data bottleneck for sequence classification.
no code implementations • EMNLP (sustainlp) 2020 • Ariadna Quattoni, Xavier Carreras
We compare a classical CNN architecture for sequence classification involving several convolutional and max-pooling layers against a simple model based on weighted finite state automata (WFA).
no code implementations • 31 May 2023 • Cesar Gonzalez-Gutierrez, Audi Primadhanty, Francesco Cazzaro, Ariadna Quattoni
Our experiments on text classification validate our hypothesis by showing that task alignment can explain the classification performance of a given representation.
no code implementations • 24 Oct 2022 • Francesco Cazzaro, Ariadna Quattoni, Xavier Carreras
We focus on sparse sequence classification, that is problems in which the target class is rare and compare three deep learning sequence classification models.
no code implementations • 11 Oct 2022 • César González-Gutiérrez, Audi Primadhanty, Francesco Cazzaro, Ariadna Quattoni
That is why the ability to train models with limited annotation budgets is of great importance.
1 code implementation • 10 Oct 2022 • Francesco Cazzaro, Davide Locatelli, Ariadna Quattoni, Xavier Carreras
Prior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks.
1 code implementation • *SEM (NAACL) 2022 • Davide Locatelli, Ariadna Quattoni
Prior to deep learning the semantic parsing community has been interested in understanding and modeling the range of possible word alignments between natural language sentences and their corresponding meaning representations.
no code implementations • ACL 2019 • Ariadna Quattoni, Xavier Carreras
Spectral models for learning weighted non-deterministic automata have nice theoretical and algorithmic properties.
no code implementations • WS 2017 • Pranava Swaroop Madhyastha, Xavier Carreras, Ariadna Quattoni
We present a low-rank multi-linear model for the task of solving prepositional phrase attachment ambiguity (PP task).
no code implementations • 9 Jun 2017 • Ariadna Quattoni, Xavier Carreras, Matthias Gallé
Spectral algorithms reduce the learning problem to the task of computing an SVD decomposition over a special type of matrix called the Hankel matrix.
no code implementations • EACL 2017 • Germ{\'a}n Ferrero, Audi Primadhanty, Ariadna Quattoni
Event Schema Induction is the task of learning a representation of events (e. g., bombing) and the roles involved in them (e. g, victim and perpetrator).
no code implementations • NAACL 2016 • Ariadna Quattoni, Arnau Ramisa, Pranava Swaroop Madhyastha, Edgar Simo-Serra, Francesc Moreno-Noguer
We address the task of annotating images with semantic tuples.
no code implementations • 22 Dec 2014 • Pranava Swaroop Madhyastha, Xavier Carreras, Ariadna Quattoni
We investigate the problem of inducing word embeddings that are tailored for a particular bilexical relation.
no code implementations • NeurIPS 2013 • Raphael Bailly, Xavier Carreras, Ariadna Quattoni
Finite-State Transducers (FST) are a standard tool for modeling paired input-output sequences and are used in numerous applications, ranging from computational biology to natural language processing.
no code implementations • CVPR 2013 • Edgar Simo-Serra, Ariadna Quattoni, Carme Torras, Francesc Moreno-Noguer
We introduce a novel approach to automatically recover 3D human pose from a single image.
Ranked #25 on 3D Human Pose Estimation on HumanEva-I