Papers by Erik-Lân Do Dinh
Weeding out Conventionalized Metaphors: A Corpus of Novel Metaphor Annotations (D18-1)
Copied to clipboard
| Challenge: | a lack of datasets distinguish between conventionalized and novel metaphors is limiting research . a novel metaphor is often overlooked or intentionally disregarded, authors say . |
| Approach: | They propose a crowdsourced annotation layer for an existing metaphor corpus to investigate novelty . they investigate correlations between concreteness ratings and more semantic features . |
| Outcome: | The proposed method combines novel metaphor annotations with concreteness ratings and semantic features. |
Predicting Humorousness and Metaphor Novelty with Gaussian Process Preference Learning (P19-1)
Copied to clipboard
| Challenge: | Inability to quantify key aspects of creative language is a frequent obstacle to natural language understanding. |
| Approach: | They propose a Bayesian approach for predicting humorousness and metaphor novelty using Gaussian process preference learning (GPPL) . |
| Outcome: | The proposed approach achieves a Spearman’s of 0.56 against gold using word embeddings and linguistic features. |
Killing Four Birds with Two Stones: Multi-Task Learning for Non-Literal Language Detection (C18-1)
Copied to clipboard
| Challenge: | idioms and metaphors are often studied in isolation, challenging the distinction . e.g., metaphorical concept mappings are ubiquitous in everyday life, thus they are ubiquitous . |
| Approach: | They propose to view the detection problem as a generalized non-literal language classification problem. |
| Outcome: | The proposed model improves on four metaphor and idiom detection tasks in two languages, English and German. |