Abigail S. Gertner

Also published as: Abigail Gertner


2022

pdf bib
Practical Attacks on Machine Translation using Paraphrase
Elizabeth M Merkhofer | John Henderson | Abigail Gertner | Michael Doyle | Lily Wong
Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)

Studies show machine translation systems are vulnerable to adversarial attacks, where a small change to the input produces an undesirable change in system behavior. This work considers whether this vulnerability exists for attacks crafted with limited information about the target: without access to ground truth references or the particular MT system under attack. It also applies a higher threshold of success, taking into account both source language meaning preservation and target language meaning degradation. We propose an attack that generates edits to an input using a finite state transducer over lexical and phrasal paraphrases and selects one perturbation for meaning preservation and expected degradation of a target system. Attacks against eight state-of-the-art translation systems covering English-German, English-Czech and English-Chinese are evaluated under black-box and transfer scenarios, including cross-language and cross-system transfer. Results suggest that successful single-system attacks seldom transfer across models, especially when crafted without ground truth, but ensembles show promise for generalizing attacks.

2019

pdf bib
MITRE at SemEval-2019 Task 5: Transfer Learning for Multilingual Hate Speech Detection
Abigail Gertner | John Henderson | Elizabeth Merkhofer | Amy Marsh | Ben Wellner | Guido Zarrella
Proceedings of the 13th International Workshop on Semantic Evaluation

This paper describes MITRE’s participation in SemEval-2019 Task 5, HatEval: Multilingual detection of hate speech against immigrants and women in Twitter. The techniques explored range from simple bag-of-ngrams classifiers to neural architectures with varied attention mechanisms. We describe several styles of transfer learning from auxiliary tasks, including a novel method for adapting pre-trained BERT models to Twitter data. Logistic regression ties the systems together into an ensemble submitted for evaluation. The resulting system was used to produce predictions for all four HatEval subtasks, achieving the best mean rank of all teams that participated in all four conditions.

2003

pdf bib
Dialogue complexity with portability? Research directions for the Information State approach
Carl Burke | Christy Doran | Abigail Gertner | Andy Gregorowicz | Lisa Harper | Joel Korb | Dan Loehr
Proceedings of the HLT-NAACL 2003 Workshop on Research Directions in Dialogue Processing

1994

pdf bib
Upholding the Maxim of Relevance during Patient-Centered Activities
Abigail S. Gertner | Bonnie L. Webber | John R. Clarke
Fourth Conference on Applied Natural Language Processing