.png){kind=icon}
.png){kind=icon}
Return
Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning
.png){kind=icon}
OA
AI
DOI：10.1162/COLI_a_00275.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Highly frequent in language and communication, metaphor represents a significant challenge for Natural Language Processing (NLP) applications. Computational work on metaphor has traditionally evolved around the use of hand-coded knowledge, making the systems hard to scale. Recent years have witnessed a rise in statistical approaches to metaphor processing. However, these approaches often require extensive human annotation effort and are predominantly evaluated within a limited domain. In contrast, we experiment with weakly supervised and unsupervised techniqueswith little or no annotationto generalize higher-level mechanisms of metaphor from distributional properties of concepts. We investigate different levels and types of supervision (learning from linguistic examples vs. learning from a given set of metaphorical mappings vs. learning without annotation) in flat and hierarchical, unconstrained and constrained clustering settings. Our aim is to identify the optimal type of supervision for a learning algorithm that discovers patterns of metaphorical association from text. In order to investigate the scalability and adaptability of our models, we applied them to data in three languages from different language groupsEnglish, Spanish, and Russianachieving state-of-the-art results with little supervision. Finally, we demonstrate that statistical methods can facilitate and scale up cross-linguistic research on metaphor.
Keywords:
CONCRETE
ENGLISH
TIME
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.3
Papers:
837
Citations:
2.7K
View more organizations