Skip to content
conftrace_
2021 ACL ACL 2021

Neural Metaphor Detection with Visibility Embeddings

Abstract

AbstractWe present new results for the problem of sequence metaphor labeling, using the recently developed Visibility Embeddings. We show that concatenating such embeddings to the input of a BiLSTM obtains consistent and significant improvements at almost no cost, and we present further improved results when visibility embeddings are combined with BERT.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Gitit Kehat, James Pustejovsky

Topics

Machine Learning > Core Methods > Classification Deep Learning > Architectures > Neural Networks Natural Language Processing > Understanding > Semantic Analysis Deep Learning > Learning Types > Representation Learning

Keywords

sequence labeling embedding learning word sense disambiguation bert model bidirectional lstm metaphor detection visibility embedding
Download PDF

More from ACL 2021

All ACL 2021 papers →
Script Parsing with Hierarchical Sequence Modelling
Incorporating EDS Graph for AMR Parsing
Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing
Inducing Language-Agnostic Multilingual Representations
Modeling Sense Structure in Word Usage Graphs with the Weighted Stochastic Block Model
Compound or Term Features? Analyzing Salience in Predicting the Difficulty of German Noun Compounds across Domains