Predicting Humorousness and Metaphor Novelty with Gaussian Process Preference Learning

1 code implementation • ACL 2019 • Edwin Simpson, Erik-L{\^a}n Do Dinh, Tristan Miller, Iryna Gurevych

The inability to quantify key aspects of creative language is a frequent obstacle to natural language understanding.

Natural Language Understanding Word Embeddings

Killing Four Birds with Two Stones: Multi-Task Learning for Non-Literal Language Detection

1 code implementation • COLING 2018 • Erik-L{\^a}n Do Dinh, Steffen Eger, Iryna Gurevych

In this paper we investigate multi-task learning for related non-literal language phenomena.

General Classification Multi-Task Learning

One Size Fits All? A simple LSTM for non-literal token and construction-level classification

no code implementations • COLING 2018 • Erik-L{\^a}n Do Dinh, Steffen Eger, Iryna Gurevych

In this paper, we tackle four different tasks of non-literal language classification: token and construction level metaphor detection, classification of idiomatic use of infinitive-verb compounds, and classification of non-literal particle verbs.

Classification General Classification +1

Token-Level Metaphor Detection using Neural Networks

no code implementations • WS 2016 • Erik-L{\^a}n Do Dinh, Iryna Gurevych

Feature Engineering Machine Translation +2

In-tool Learning for Selective Manual Annotation in Large Corpora

no code implementations • IJCNLP 2015 • Erik-L{\^a}n Do Dinh, Richard Eckart de Castilho, Iryna Gurevych