13 citations · 32 across the 11 of their papers we have counts for
11 papers
GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks
Amirhossein Vahdat, Thierry Badard, Luc Lamontagne
Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. This omission is critical as ret…
Preventing RNN from Using Sequence Length as a Feature
Jean-Thomas Baillargeon, Hélène Cossette, Luc Lamontagne
Recurrent neural networks are deep learning topologies that can be trained to classify long documents. However, in our recent work, we found a critical problem with these cells: th…
Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models
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 leng…
Multinational Address Parsing: A Zero-Shot Evaluation
Marouane Yassine, David Beauchemin, François Laviolette +1
Address parsing consists of identifying the segments that make up an address, such as a street name or a postal code. Because of its importance for tasks like record linkage, addre…
Geographic ratemaking with spatial embeddings
Christopher Blier-Wong, Hélène Cossette, Luc Lamontagne +1
Spatial data is a rich source of information for actuarial applications: knowledge of a risk's location could improve an insurance company's ratemaking, reserving or risk managemen…
Rethinking Representations in P&C Actuarial Science with Deep Neural Networks
Christopher Blier-Wong, Jean-Thomas Baillargeon, Hélène Cossette +2
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. In particular, many…
Generating Intelligible Plumitifs Descriptions: Use Case Application with Ethical Considerations
David Beauchemin, Nicolas Garneau, Eve Gaumond +3
Plumitifs (dockets) were initially a tool for law clerks. Nowadays, they are used as summaries presenting all the steps of a judicial case. Information concerning parties' identity…
Leveraging Subword Embeddings for Multinational Address Parsing
Marouane Yassine, David Beauchemin, François Laviolette +1
Address parsing consists of identifying the segments that make up an address such as a street name or a postal code. Because of its importance for tasks like record linkage, addres…
Attending Form and Context to Generate Specialized Out-of-VocabularyWords Representations
Nicolas Garneau, Jean-Samuel Leboeuf, Yuval Pinter +1
We propose a new contextual-compositional neural network layer that handles out-of-vocabulary (OOV) words in natural language processing (NLP) tagging tasks. This layer consists of…
A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well
Nicolas Garneau, Mathieu Godbout, David Beauchemin +2
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. We…
Predicting and interpreting embeddings for out of vocabulary words in downstream tasks
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. We implement a network that predicts useful embeddings for OOV…