John Henderson

Also published as: John C. Henderson


2022

pdf
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.

2021

pdf
Perceptual Models of Machine-Edited Text
Elizabeth Merkhofer | Monica-Ann Mendoza | Rebecca Marvin | John Henderson
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

2019

pdf
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.

2018

pdf
MITRE at SemEval-2018 Task 11: Commonsense Reasoning without Commonsense Knowledge
Elizabeth Merkhofer | John Henderson | David Bloom | Laura Strickhart | Guido Zarrella
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper describes MITRE’s participation in SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. The techniques explored range from simple bag-of-ngrams classifiers to neural architectures with varied attention and alignment mechanisms. Logistic regression ties the systems together into an ensemble submitted for evaluation. The resulting system answers reading comprehension questions with 82.27% accuracy.

2017

pdf
MITRE at SemEval-2017 Task 1: Simple Semantic Similarity
John Henderson | Elizabeth Merkhofer | Laura Strickhart | Guido Zarrella
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

This paper describes MITRE’s participation in the Semantic Textual Similarity task (SemEval-2017 Task 1), which evaluated machine learning approaches to the identification of similar meaning among text snippets in English, Arabic, Spanish, and Turkish. We detail the techniques we explored ranging from simple bag-of-ngrams classifiers to neural architectures with varied attention and alignment mechanisms. Linear regression is used to tie the systems together into an ensemble submitted for evaluation. The resulting system is capable of matching human similarity ratings of image captions with correlations of 0.73 to 0.83 in monolingual settings and 0.68 to 0.78 in cross-lingual conditions, demonstrating the power of relatively simple approaches.

2015

pdf bib
MITRE: Seven Systems for Semantic Similarity in Tweets
Guido Zarrella | John Henderson | Elizabeth M. Merkhofer | Laura Strickhart
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

2013

pdf
Discriminating Non-Native English with 350 Words
John Henderson | Guido Zarrella | Craig Pfeifer | John D. Burger
Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications

pdf
Learning from OzCLO, the Australian Computational and Linguistics Olympiad
Dominique Estival | John Henderson | Mary Laughren | Diego Mollá | Cathy Bow | Rachel Nordlinger | Verna Rieschild | Andrea C. Schalley | Alexander W. Stanley | Colette Mrowa-Hopkins
Proceedings of the Fourth Workshop on Teaching NLP and CL

2012

pdf
Navigating Large Comment Threads with CoFi
Christine Doran | Guido Zarrella | John C. Henderson
Proceedings of the Demonstration Session at the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2011

pdf
Discriminating Gender on Twitter
John D. Burger | John Henderson | George Kim | Guido Zarrella
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

2005

pdf
Gaming Fluency: Evaluating the Bounds and Expectations of Segment-based Translation Memory
John Henderson | William Morgan
Proceedings of the ACL Workshop on Building and Using Parallel Texts

2004

pdf
MiTAP for SARS Detection
Laurie E. Damianos | Samuel Bayer | Michael A. Chisholm | John Henderson | Lynette Hirschman | William Morgan | Marc Ubaldino | Guido Zarrella | James M. Wilson V | Marat G. Polyak
Demonstration Papers at HLT-NAACL 2004

pdf
Direct Maximization of Average Precision by Hill-Climbing, with a Comparison to a Maximum Entropy Approach
William Morgan | Warren Greiff | John Henderson
Proceedings of HLT-NAACL 2004: Short Papers

2003

pdf
Word Alignment Baselines
John C. Henderson
Proceedings of the HLT-NAACL 2003 Workshop on Building and Using Parallel Texts: Data Driven Machine Translation and Beyond

pdf
Exploiting Diversity for Answering Questions
John Burger | John Henderson
Companion Volume of the Proceedings of HLT-NAACL 2003 - Short Papers

2002

pdf
Statistical Named Entity Recognizer Adaptation
John D. Burger | John C. Henderson | William T. Morgan
COLING-02: The 6th Conference on Natural Language Learning 2002 (CoNLL-2002)

2001

pdf
Integrated Feasibility Experiment for Bio-Security: IFE-Bio, A TIDES Demonstration
Lynette Hirschman | Kris Concepcion | Laurie Damianos | David Day | John Delmore | Lisa Ferro | John Griffith | John Henderson | Jeff Kurtz | Inderjeet Mani | Scott Mardis | Tom McEntee | Keith Miller | Beverly Nunam | Jay Ponte | Florence Reeder | Ben Wellner | George Wilson | Alex Yeh
Proceedings of the First International Conference on Human Language Technology Research

2000

pdf bib
Automatic Grammar Induction: Combining, Reducing and Doing Nothing
Eric Brill | John C. Henderson | Grace Ngai
Proceedings of the Sixth International Workshop on Parsing Technologies

This paper surveys three research directions in parsing. First, we look at methods for both automatically generating a set of diverse parsers and combining the outputs of different parsers into a single parse. Next, we will discuss a parsing method known as transformation-based parsing. This method, though less accurate than the best current corpus-derived parsers, is able to parse quite accurately while learning only a small set of easily understood rules, as opposed to the many-megabyte parameter files learned by other techniques. Finally, we review a recent study exploring how people and machines compare at the task of creating a program to automatically annotate noun phrases.

pdf
Coaxing Confidences from an Old Freind: Probabilistic Classifications from Transformation Rule Lists
Radu Florian | John C. Henderson | Grace Ngai
2000 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora

pdf
Bagging and Boosting a Treebank Parser
John C. Henderson | Eric Brill
1st Meeting of the North American Chapter of the Association for Computational Linguistics

pdf
ATLAS: A Flexible and Extensible Architecture for Linguistic Annotation
Steven Bird | David Day | John Garofolo | John Henderson | Christophe Laprun | Mark Liberman
Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00)

pdf
A Framework for Cross-Document Annotation
David Day | Alan Goldschen | John Henderson
Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00)

1999

pdf
Exploiting Diversity in Natural Language Processing: Combining Parsers
John C. Henderson | Eric Brill
1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora

1998

pdf
Beyond N -Grams: Can Linguistic Sophistication Improve Language Modeling?
Eric Brill | Radu Florian | John C. Henderson | Lidia Mangu
36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 1

pdf
Beyond N-Grams: Can Linguistic Sophistication Improve Language Modeling?
Eric Brill | Radu Florian | John C. Henderson | Lidia Mangu
COLING 1998 Volume 1: The 17th International Conference on Computational Linguistics

1997

pdf
String Transformation Learning
Giorgio Satta | John C. Henderson
35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics