Surface Realization Using Pretrained Language Models

no code implementations • MSR (COLING) 2020 • Farhood Farahnak, Laya Rafiee, Leila Kosseim, Thomas Fevens

In the context of Natural Language Generation, surface realization is the task of generating the linear form of a text following a given grammar.

Language Modelling Sentence +1

Transparent Anomaly Detection via Concept-based Explanations

no code implementations • 16 Oct 2023 • Laya Rafiee Sevyeri, Ivaxi Sheth, Farhood Farahnak, Samira Ebrahimi Kahou, Shirin Abbasinejad Enger

The task of anomaly detection (AD) focuses on finding whether a given sample follows the learned distribution.

Anomaly Detection Classification +2

Source-free Domain Adaptation Requires Penalized Diversity

no code implementations • 6 Apr 2023 • Laya Rafiee Sevyeri, Ivaxi Sheth, Farhood Farahnak, Alexandre See, Samira Ebrahimi Kahou, Thomas Fevens, Mohammad Havaei

In addition, PD is augmented with a weighted MI maximization objective for label distribution shift.

Image Classification Source-Free Domain Adaptation +1

The Concordia NLG Surface Realizer at SRST 2019

no code implementations • WS 2019 • Farhood Farahnak, Laya Rafiee, Leila Kosseim, Thomas Fevens

This paper presents the model we developed for the shallow track of the 2019 NLG Surface Realization Shared Task.

CLaC @ DEFT 2018: Sentiment analysis of tweets on transport from \^Ile-de-France

no code implementations • JEPTALNRECITAL 2018 • Simon Jacques, Farhood Farahnak, Leila Kosseim

CLaC @ DEFT 2018: Analysis of tweets on transport on the {\^I}le-de-France This paper describes the system deployed by the CLaC lab at Concordia University in Montreal for the DEFT 2018 shared task.

Sentiment Analysis Task 2