no code implementations • EMNLP (sustainlp) 2021 • Maria Glenski, William I. Sealy, Kate Miller, Dustin Arendt
Traditional synonym recommendations often include ill-suited suggestions for writer’s specific contexts.
1 code implementation • NAACL (DaSH) 2021 • Kayla Duskin, Shivam Sharma, Ji Young Yun, Emily Saldanha, Dustin Arendt
Current methods for evaluation of natural language generation models focus on measuring text quality but fail to probe the model creativity, i. e., its ability to generate novel but coherent text sequences not seen in the training corpus.
no code implementations • NAACL (SocialNLP) 2021 • Maria Glenski, Ellyn Ayton, Robin Cosbey, Dustin Arendt, Svitlana Volkova
With the increasing use of machine-learning driven algorithmic judgements, it is critical to develop models that are robust to evolving or manipulated inputs.
no code implementations • RDSM (COLING) 2020 • Maria Glenski, Ellyn Ayton, Robin Cosbey, Dustin Arendt, Svitlana Volkova
Our analyses reveal a significant drop in performance when testing neural models on out-of-domain data and non-English languages that may be mitigated using diverse training data.
no code implementations • EACL 2021 • Winston Wu, Dustin Arendt, Svitlana Volkova
We evaluate neural model robustness to adversarial attacks using different types of linguistic unit perturbations {--} character and word, and propose a new method for strategic sentence-level perturbations.
no code implementations • 1 Jan 2021 • Emily Saldanha, Dustin Arendt, Svitlana Volkova
Many existing algorithms for the discovery of causal structure from observational data rely on evaluating the conditional independence relationships among features to account for the effects of confounding.
no code implementations • 27 Sep 2020 • Brittany Davis, Maria Glenski, William Sealy, Dustin Arendt
However, the focus on trust is too narrow, and has led the research community astray from tried and true empirical methods that produced more defensible scientific knowledge about people and explanations.
BIG-bench Machine Learning Explainable Artificial Intelligence (XAI)
no code implementations • 1 May 2020 • Winston Wu, Dustin Arendt, Svitlana Volkova
We evaluate machine comprehension models' robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level.
no code implementations • 17 Oct 2017 • Maria Glenski, Ellyn Ayton, Dustin Arendt, Svitlana Volkova
We evaluate the predictive power of models trained on varied text and image representations extracted from tweets.
no code implementations • WS 2017 • Lawrence Phillips, Kyle Shaffer, Dustin Arendt, Nathan Hodas, Svitlana Volkova
Language in social media is a dynamic system, constantly evolving and adapting, with words and concepts rapidly emerging, disappearing, and changing their meaning.