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 and context.
In this work we perform a controlled study of human language use in a competitive team-based game, and search for useful lessons for structuring communication protocol between autonomous agents.
This provides a visual grounding of the message, similar to an enhanced observation of the world, which may include objects outside of the listening agent's field-of-view.
We propose a hierarchical meta-learning-inspired model for music source separation (Meta-TasNet) in which a generator model is used to predict the weights of individual extractor models.
Ranked #16 on Music Source Separation on MUSDB18
Statistical morphological inflectors are typically trained on fully supervised, type-level data.
Neural architectures are prominent in the construction of language models (LMs).
Comprehending lyrics, as found in songs and poems, can pose a challenge to human and machine readers alike.
In order to extract event information from text, a machine reading model must learn to accurately read and interpret the ways in which that information is expressed.
Given that in practice training data is scarce for all but a small set of problems, a core question is how to incorporate prior knowledge into a model.