no code implementations • INLG (ACL) 2021 • Nicolas Garneau, Luc Lamontagne
Our submission consists in fact of two submissions; we first analyze solely the performance of the rules and classifiers (pre-annotations), and then the human evaluation aided by the former pre-annotations using the web interface (hybrid).
no code implementations • 16 Dec 2022 • Jean-Thomas Baillargeon, Hélène Cossette, Luc Lamontagne
Recurrent neural networks are deep learning topologies that can be trained to classify long documents.
no code implementations • 16 Dec 2022 • Jean-Thomas Baillargeon, Luc Lamontagne
Classification algorithms using Transformer architectures can be affected by the sequence length learning problem whenever observations from different classes have a different length distribution.
1 code implementation • 7 Dec 2021 • Marouane Yassine, David Beauchemin, François Laviolette, Luc Lamontagne
While these models yield notable results, previous work on neural networks has only focused on parsing addresses from a single source country.
no code implementations • 26 Apr 2021 • Christopher Blier-Wong, Hélène Cossette, Luc Lamontagne, Etienne Marceau
This paper presents a method based on data (instead of smoothing historical insurance claim losses) to construct a geographic ratemaking model.
no code implementations • 11 Feb 2021 • Christopher Blier-Wong, Jean-Thomas Baillargeon, Hélène Cossette, Luc Lamontagne, Etienne Marceau
Insurance companies gather a growing variety of data for use in the insurance process, but most traditional ratemaking models are not designed to support them.
Representation Learning Applications
no code implementations • INLG (ACL) 2020 • David Beauchemin, Nicolas Garneau, Eve Gaumond, Pierre-Luc Déziel, Richard Khoury, Luc Lamontagne
Plumitifs (dockets) were initially a tool for law clerks.
3 code implementations • 29 Jun 2020 • Marouane Yassine, David Beauchemin, François Laviolette, Luc Lamontagne
We propose an approach in which we employ subword embeddings and a Recurrent Neural Network architecture to build a single model capable of learning to parse addresses from multiple countries at the same time while taking into account the difference in languages and address formatting systems.
no code implementations • 14 Dec 2019 • Nicolas Garneau, Jean-Samuel Leboeuf, Yuval Pinter, Luc Lamontagne
We propose a new contextual-compositional neural network layer that handles out-of-vocabulary (OOV) words in natural language processing (NLP) tagging tasks.
1 code implementation • LREC 2020 • Nicolas Garneau, Mathieu Godbout, David Beauchemin, Audrey Durand, Luc Lamontagne
In this paper, we reproduce the experiments of Artetxe et al. (2018b) regarding the robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings.
no code implementations • WS 2018 • Nicolas Garneau, Jean-Samuel Leboeuf, Luc Lamontagne
We propose a novel way to handle out of vocabulary (OOV) words in downstream natural language processing (NLP) tasks.