← Back to papers
2020 COLING COLING 2020

LAST at SemEval-2020 Task 10: Finding Tokens to Emphasise in Short Written Texts with Precomputed Embedding Models and LightGBM

Abstract

AbstractTo select tokens to be emphasised in short texts, a system mainly based on precomputed embedding models, such as BERT and ELMo, and LightGBM is proposed. Its performance is low. Additional analyzes suggest that its effectiveness is poor at predicting the highest emphasis scores while they are the most important for the challenge and that it is very sensitive to the specific instances provided during learning.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — precomputed embedding
🐣 Hot Topic Early Bird — token classification
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Security & Privacy, Speech & Audio

Authors

Yves Bestgen

Topics

Machine Learning > Core Methods > Classification Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Transformers

Keywords

token classification bert embedding elmo embedding precomputed embedding
Download PDF

Related papers

Persuasiveness of News Editorials depending on Ideology and Personality 2020
A Graph Representation of Semi-structured Data for Web Question Answering 2020
Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations 2020
Hierarchical Chinese Legal event extraction via Pedal Attention Mechanism 2020
End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network 2020