Séminaires RALI-OLST

Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition

Abbas Ghaddar (abbas (point) ghaddar <at> huawei (point) com)

Huawei Montreal

Le mercredi 27 octobre 2021 à 11 h 30

Réunion Zoom (ci-dessous)

In this work, we examine the ability of NER models to use contextual information when predicting the type of an ambiguous entity. We introduce NRB, a new testbed carefully designed to diagnose Name Regularity Bias of NER models. Our results indicate that all state-of-the-art models we tested show such a bias; BERT fine-tuned models significantly outperforming feature-based (LSTM-CRF) ones on NRB, despite having comparable (sometimes lower) performance on standard benchmarks.To mitigate this bias, we propose a novel model-agnostic training method that adds learnable adversarial noise to some entity mentions, thus enforcing models to focus more strongly on the contextual signal, leading to significant gains on NRB. Combining it with two other training strategies, data augmentation and parameter freezing, leads to further gains.

La présentation sera donnée en français

Joignez-vous à nous avec Zoom à l'aide de cette URL.
ID de réunion : 916 9097 5818, Code : 343273.
Numéros de téléphone : https://umontreal.zoom.us/u/abitNZzLg.
One tap mobile : +14388097799,,91690975818#,,,,,,0#,,343273#

Pour recevoir les annonces hebdomadaires par courriel, envoyez un message à l'adresse majordomo@iro.umontreal.ca. Il suffit d'envoyer un message ne contenant que la ligne 'subscribe ralli' (sans les apostrophes).

Liste de tous les séminaires pour l'année :

1991 1992 1993 1994 1995 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021