papers AI Learner
The Github is limit! Click to go to the new site.

Learning Outside the Box: Discourse-level Features Improve Metaphor Identification

2019-04-03
Jesse Mu, Helen Yannakoudakis, Ekaterina Shutova

Abstract

Most current approaches to metaphor identification use restricted linguistic contexts, e.g. by considering only a verb’s arguments or the sentence containing a phrase. Inspired by pragmatic accounts of metaphor, we argue that broader discourse features are crucial for better metaphor identification. We train simple gradient boosting classifiers on representations of an utterance and its surrounding discourse learned with a variety of document embedding methods, obtaining near state-of-the-art results on the 2018 VU Amsterdam metaphor identification task without the complex metaphor-specific features or deep neural architectures employed by other systems. A qualitative analysis further confirms the need for broader context in metaphor processing.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.02246

PDF

http://arxiv.org/pdf/1904.02246


Comments

Content