A neural network to classify metaphorical violence on cable news
This work addresses the challenge of metaphor classification for researchers and analysts in computational linguistics, though it appears incremental as it builds on existing annotation tools and methods.
The paper tackles the problem of automatically identifying and annotating metaphors in text corpora by developing a neural network system that learns from user annotations in an interactive web app, enabling transfer learning between different metaphor classes with measurable reliability.
I present here an experimental system for identifying and annotating metaphor in corpora. It is designed to plug in to Metacorps, an experimental web app for annotating metaphor. As Metacorps users annotate metaphors, the system will use user annotations as training data. When the system is confident, it will suggest an identification and an annotation. Once approved by the user, this becomes more training data. This naturally allows for transfer learning, where the system can, with some known degree of reliability, classify one class of metaphor after only being trained on another class of metaphor. For example, in our metaphorical violence project, metaphors may be classified by the network they were observed on, the grammatical subject or object of the violence metaphor, or the violent word used (hit, attack, beat, etc.).