Name
Abstract | ||
|---|---|---|
Most current approaches to metaphor identification use restricted linguistic contexts, e.g. by considering only a verbu0027s 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. |
Year | Venue | Field |
|---|---|---|
2019 | arXiv: Computation and Language | Computer science,Cognitive science,Artificial intelligence,Natural language processing,Metaphor |
DocType | Volume | Citations |
Journal | abs/1904.02246 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jesse Mu | 1 | 0 | 2.03 |
| Helen Yannakoudakis | 2 | 154 | 13.22 |
| Ekaterina Shutova | 3 | 228 | 21.51 |