8 papers · 1 filter
Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem
Qiang Zhang, Jason Naradowsky, Yusuke Miyao
We introduce the task of implicit offensive text detection in dialogues, where a statement may have either an offensive or non-offensive interpretation, depending on the listener a…
Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman
Takuma Yoneda, Matthew R. Walter, Jason Naradowsky
In multi-agent learning, agents must coordinate with each other in order to succeed. For humans, this coordination is typically accomplished through the use of language. In this wo…
Emergent Communication with World Models
Alexander I. Cowen-Rivers, Jason Naradowsky
We introduce Language World Models, a class of language-conditional generative model which interpret natural language messages by predicting latent codes of future observations. Th…
Machine Translation System Selection from Bandit Feedback
Jason Naradowsky, Xuan Zhang, Kevin Duh
Adapting machine translation systems in the real world is a difficult problem. In contrast to offline training, users cannot provide the type of fine-grained feedback (such as corr…
A Structured Variational Autoencoder for Contextual Morphological Inflection
Lawrence Wolf-Sonkin, Jason Naradowsky, Sabrina J. Mielke +1
Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively explo…
Hypothesis Only Baselines in Natural Language Inference
Adam Poliak, Jason Naradowsky, Aparajita Haldar +2
We propose a hypothesis only baseline for diagnosing Natural Language Inference (NLI). Especially when an NLI dataset assumes inference is occurring based purely on the relationshi…