conftrace_

2018 EMNLP EMNLP 2018

Amobee at IEST 2018: Transfer Learning from Language Models

Abstract

AbstractThis paper describes the system developed at Amobee for the WASSA 2018 implicit emotions shared task (IEST). The goal of this task was to predict the emotion expressed by missing words in tweets without an explicit mention of those words. We developed an ensemble system consisting of language models together with LSTM-based networks containing a CNN attention mechanism. Our approach represents a novel use of language models—specifically trained on a large Twitter dataset—to predict and classify emotions. Our system reached 1st place with a macro F1 score of 0.7145.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Alon Rozental, Daniel Fleischer, Zohar Kelrich

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Core Methods > Classification Machine Learning > Learning Types > Transfer Learning Natural Language Processing > Applications > Sentiment Analysis Deep Learning > Learning Types > Representation Learning Deep Learning > Learning Types > Transfer Learning

Keywords

transfer learning ensemble learning attention mechanism language model emotion classification lstm network ensemble system cnn attention mechanism implicit emotion classification

More from EMNLP 2018

All EMNLP 2018 papers →

Language Independent Sentiment Analysis with Sentiment-Specific Word Embeddings

Creating a Dataset for Multilingual Fine-grained Emotion-detection Using Gamification-based Annotation

IEST: WASSA-2018 Implicit Emotions Shared Task

IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations

NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification

Sentiment analysis under temporal shift