Adversarial Multi-task Learning for End-to-end Metaphor Detection

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

silasthu/admul — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Metaphor detection (MD) suffers from limited training data. In this paper, we started with a linguistic rule called Metaphor Identification Procedure and then proposed a novel multi-task learning framework to transfer knowledge in basic sense discrimination (BSD) to MD. BSD is constructed from word sense disambiguation (WSD), which has copious amounts of data. We leverage adversarial training to align the data distributions of MD and BSD in the same feature space, so task-invariant representations can be learned. To capture fine-grained alignment patterns, we utilize the multi-mode structures of MD and BSD. Our method is totally end-to-end and can mitigate the data scarcity problem in MD. Competitive results are reported on four public datasets. Our code and datasets are available.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.16638")
get_code_for_paper("2305.16638")
have("2305.16638")

Connect an agent — have() is free.