activity
20172022
collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2022

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…

cs.CL2020

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…

cs.CL2020

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…

cs.CL2020

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…

cs.CL2018

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…

cs.CL2018

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…